[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-JuliaReinforcementLearning--ReinforcementLearning.jl":3,"tool-JuliaReinforcementLearning--ReinforcementLearning.jl":61},[4,18,26,36,44,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,"2026-04-05T11:01:52",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",158594,2,"2026-04-16T23:34:05",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",108322,"2026-04-10T11:39:34",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"status":17},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[52,13,15,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":32,"last_commit_at":59,"category_tags":60,"status":17},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[52,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":72,"owner_name":72,"owner_avatar_url":73,"owner_bio":74,"owner_company":75,"owner_location":75,"owner_email":75,"owner_twitter":75,"owner_website":76,"owner_url":77,"languages":78,"stars":87,"forks":88,"last_commit_at":89,"license":90,"difficulty_score":32,"env_os":91,"env_gpu":91,"env_ram":91,"env_deps":92,"category_tags":100,"github_topics":101,"view_count":32,"oss_zip_url":75,"oss_zip_packed_at":75,"status":17,"created_at":107,"updated_at":108,"faqs":109,"releases":110},8257,"JuliaReinforcementLearning\u002FReinforcementLearning.jl","ReinforcementLearning.jl","A reinforcement learning package for Julia","ReinforcementLearning.jl 是一个专为 Julia 语言打造的强化学习研究工具包，旨在帮助开发者高效地构建、测试和比较各类强化学习算法。它主要解决了从传统表格方法到现代深度强化学习算法在实验复现、组件复用及快速原型开发上的痛点。\n\n这款工具非常适合研究人员、算法工程师以及希望深入探索强化学习领域的开发者使用。其核心设计理念遵循“先跑通、再优化、后加速”，提供了高度模块化且易于扩展的接口。用户只需几行代码，即可灵活组合策略（Policy）、环境（Environment）、停止条件与监控钩子（Hook）这四大核心组件，快速搭建起完整的实验流程。例如，用户可以轻松调用内置的 CartPole 环境与随机策略进行基准测试，或自定义新算法进行深度评估。\n\nReinforcementLearning.jl 的独特亮点在于其出色的可复现性与实验便捷性，不仅内置了丰富的经典环境与算法实现，还通过清晰的结构设计降低了新手入门门槛，让复杂的强化学习实验变得像搭积木一样简单直观。无论是学术科研还是工程验证，它都能提供稳定可靠的支持。","\u003C!-- ```@raw html -->\n\u003Cdiv align=\"center\">\n  \u003Cp>\n  \u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fraw\u002Fmain\u002Fdocs\u002Fsrc\u002Fassets\u002Flogo.svg?sanitize=true\" width=\"320px\">\n  \u003C\u002Fp>\n  \n  \u003Cp>\n  \u003Ca href=\"https:\u002F\u002Fwiki.c2.com\u002F?MakeItWorkMakeItRightMakeItFast\">\"Make It Work Make It Right Make It Fast\"\u003C\u002Fa>\n  \u003C\u002Fp>\n  \n  \u003Cp>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Factions?query=workflow%3ACI\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fworkflows\u002FCI\u002Fbadge.svg\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fjuliahub.com\u002Fui\u002FPackages\u002FReinforcementLearning\u002F6l2TO\">\u003Cimg src=\"https:\u002F\u002Fjuliahub.com\u002Fdocs\u002FReinforcementLearning\u002Fpkgeval.svg\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fjuliahub.com\u002Fui\u002FPackages\u002FReinforcementLearning\u002F6l2TO\">\u003Cimg src=\"https:\u002F\u002Fjuliahub.com\u002Fdocs\u002FReinforcementLearning\u002Fversion.svg\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fblob\u002Fmain\u002FLICENSE.md\">\u003Cimg src=\"http:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-brightgreen.svg?style=flat\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fjulialang.org\u002Fslack\u002F\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FChat%20on%20Slack-%23reinforcement--learnin-ff69b4\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FSciML\u002FColPrac\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FColPrac-Contributor's%20Guide-blueviolet\">\u003C\u002Fa>\n  \u003C\u002Fp>\n\n\u003C\u002Fdiv>\n\u003C!-- ``` -->\n\n---\n\n[**ReinforcementLearning.jl**](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl),\nas the name says, is a package for reinforcement learning research in Julia.\n\nOur design principles are:\n\n- **Reusability and extensibility**: Provide elaborately designed components and\n  interfaces to help users implement new algorithms.\n- **Easy experimentation**: Make it easy for new users to run benchmark\n  experiments, compare different algorithms, evaluate and diagnose agents.\n- **Reproducibility**: Facilitate reproducibility from traditional tabular\n  methods to modern deep reinforcement learning algorithms.\n  \n\n## 🏹 Get Started\n\n```julia\njulia> ] add ReinforcementLearning\n\njulia> using ReinforcementLearning\n\njulia> run(\n           RandomPolicy(),\n           CartPoleEnv(),\n           StopAfterNSteps(1_000),\n           TotalRewardPerEpisode()\n       )\n```\n\nThe above simple example demonstrates four core components in a general\nreinforcement learning experiment:\n\n- **Policy**. The\n  [`RandomPolicy`](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fdocs\u002Frlcore\u002F#ReinforcementLearningCore.RandomPolicy)\n  is the simplest instance of\n  [`AbstractPolicy`](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fdocs\u002Frlbase\u002F#ReinforcementLearningBase.AbstractPolicy).\n  It generates a random action at each step.\n\n- **Environment**. The\n  [`CartPoleEnv`](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fdocs\u002Frlenvs\u002F#ReinforcementLearningEnvironments.CartPoleEnv-Tuple%7B%7D)\n  is a typical\n  [`AbstractEnv`](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fdocs\u002Frlbase\u002F#ReinforcementLearningBase.AbstractEnv)\n  to test reinforcement learning algorithms.\n\n- **Stop Condition**. The\n  [`StopAfterNSteps(1_000)`](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fdocs\u002Frlcore\u002F#ReinforcementLearningCore.StopAfterNSteps)\n  is to inform that our experiment should stop after\n  `1_000` steps.\n\n- **Hook**. The\n  [`TotalRewardPerEpisode`](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fdocs\u002Frlcore\u002F#ReinforcementLearningCore.TotalRewardPerEpisode)\n  structure is one of the most common\n  [`AbstractHook`](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fdocs\u002Frlcore\u002F#ReinforcementLearningCore.AbstractHook)s.\n  It is used to collect the total reward of each episode in an experiment.\n\nCheck out the [tutorial](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fdocs\u002Ftutorial\u002F) page to learn how these four\ncomponents are assembled together to solve many interesting problems. We also\nwrite [blog](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fblog\u002F) occasionally to\nexplain the implementation details of some algorithms. Among them, the most\nrecommended one is [*An Introduction to\nReinforcementLearning.jl*](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fblog\u002Fan_introduction_to_reinforcement_learning_jl_design_implementations_thoughts\u002F),\nwhich explains the design idea of this package.\n\n## 🙋 Why ReinforcementLearning.jl?\n\n### 🚀 Fast Speed\n\n[TODO:]\n\n### 🧰 Feature Rich\n\n[TODO:]\n\n## 🌲 Project Structure\n\n`ReinforcementLearning.jl` itself is just a wrapper around several other\nsubpackages. The relationship between them is depicted below:\n\n\u003C!-- ```@raw html -->\n\u003Cpre>+-----------------------------------------------------------------------------------+\n|                                                                                   |\n|  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\">ReinforcementLearning.jl\u003C\u002Fa>                                                         |\n|                                                                                   |\n|      +------------------------------+                                             |\n|      | \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Ftree\u002Fmain\u002Fsrc\u002FReinforcementLearningBase\">ReinforcementLearningBase.jl\u003C\u002Fa> |                                             |\n|      +----|-------------------------+                                             |\n|           |                                                                       |\n|           |     +--------------------------------------+                          |\n|           +---->+ \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Ftree\u002Fmain\u002Fsrc\u002FReinforcementLearningEnvironments\">ReinforcementLearningEnvironments.jl\u003C\u002Fa> |                          |\n|           |     +--------------------------------------+                          |\n|           |                                                                       |\n|           |     +------------------------------+                                  |\n|           +---->+ \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Ftree\u002Fmain\u002Fsrc\u002FReinforcementLearningCore\">ReinforcementLearningCore.jl\u003C\u002Fa> |                                  |\n|                 +----|-------------------------+                                  |\n|                      |                                                            |\n|                      |     +-----------------------------+                        |\n|                      +---->+ \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Ftree\u002Fmain\u002Fsrc\u002FReinforcementLearningZoo\">ReinforcementLearningZoo.jl\u003C\u002Fa> |                        |\n|                            +----|------------------------+                        |\n|                                 |                                                 |\n|                                 |     +-------------------------------------+     |\n|                                 +---->+ \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FDistributedReinforcementLearning.jl\">DistributedReinforcementLearning.jl\u003C\u002Fa> |     |\n|                                       +-------------------------------------+     |\n|                                                                                   |\n+------|----------------------------------------------------------------------------+\n       |\n       |     +-------------------------------------+\n       +---->+ \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Ftree\u002Fmain\u002Fsrc\u002FReinforcementLearningExperiments\">ReinforcementLearningExperiments.jl\u003C\u002Fa> |\n       |     +-------------------------------------+\n       |\n       |     +----------------------------------------+\n       +---->+ \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearningAnIntroduction.jl\">ReinforcementLearningAnIntroduction.jl\u003C\u002Fa> |\n             +----------------------------------------+\n\n\u003C\u002Fpre>\n\u003C!-- ``` -->\n\n## ✋ Getting Help\nAre you looking for help with ReinforcementLearning.jl? Here are ways to find help:\n1. Read the online documentation! Most likely the answer is already provided in an example or in the API documents. Search using the search bar in the upper left. \n\u003C!-- cspell:disable-next -->\n2. Chat with us in [Julia Slack](https:\u002F\u002Fjulialang.org\u002Fslack\u002F) in the #reinforcement-learnin channel.\n3. Post a question in the [Julia discourse](https:\u002F\u002Fdiscourse.julialang.org\u002F) forum in the category \"Machine Learning\" and use \"reinforcement-learning\" as a tag.\n4. For issues with unexpected behavior or defects in ReinforcementLearning.jl, then please open an issue on the ReinforcementLearning [GitHub page](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl) with a minimal working example and steps to reproduce. \n\n## 🖖 Supporting\n\n`ReinforcementLearning.jl` is a MIT licensed open source project with its\nongoing development made possible by many contributors in their spare time.\nHowever, modern reinforcement learning research requires huge computing\nresource, which is unaffordable for individual contributors. So if you or your\norganization could provide the computing resource in some degree and would like\nto cooperate in some way, please contact us!\n\nThis package is written in pure Julia. Please consider [supporting the JuliaLang org](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FJuliaLang)\nif you find this package useful. ❤\n\n## ✍️ Citing\n\nIf you use `ReinforcementLearning.jl` in a scientific publication, we would\nappreciate references to the [CITATION.bib](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fblob\u002Fmain\u002FCITATION.bib).\n\n## ✨ Contributors\n\nThanks goes to these wonderful people ([emoji key](https:\u002F\u002Fallcontributors.org\u002Fdocs\u002Fen\u002Femoji-key)):\n\n\u003C!-- ```@raw html -->\n\u003C!-- cSpell:disable -->\n\u003C!-- ALL-CONTRIBUTORS-LIST:START - Do not remove or modify this section -->\n\u003C!-- prettier-ignore-start -->\n\u003C!-- markdownlint-disable -->\n\u003Ctable>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"http:\u002F\u002Flcn.epfl.ch\u002F~brea\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_141891678f7c.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>jbrea\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=jbrea\" title=\"Code\">💻\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=jbrea\" title=\"Documentation\">📖\u003C\u002Fa> \u003Ca href=\"#maintenance-jbrea\" title=\"Maintenance\">🚧\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Ftianjun.me\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_d4860ef85a5b.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Jun Tian\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=findmyway\" title=\"Code\">💻\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=findmyway\" title=\"Documentation\">📖\u003C\u002Fa> \u003Ca href=\"#maintenance-findmyway\" title=\"Maintenance\">🚧\u003C\u002Fa> \u003Ca href=\"#ideas-findmyway\" title=\"Ideas, Planning, & Feedback\">🤔\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Famanbh\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_879705d44ba5.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Aman Bhatia\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=amanbh\" title=\"Documentation\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Favt.im\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_3320e58baa12.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Alexander Terenin\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=aterenin\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FSid-Bhatia-0\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_10b1b6ac873f.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Sid-Bhatia-0\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=Sid-Bhatia-0\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fnorci\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_d867920150fc.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>norci\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=norci\" title=\"Code\">💻\u003C\u002Fa> \u003Ca href=\"#maintenance-norci\" title=\"Maintenance\">🚧\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fsriram13m\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_3b2a578cf47f.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Sriram\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=sriram13m\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fgpavanb1\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_6880dba73945.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Pavan B Govindaraju\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=gpavanb1\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAlexLewandowski\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_7004ba176508.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Alex Lewandowski\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=AlexLewandowski\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FRajGhugare19\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_59b06793660d.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Raj Ghugare\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=RajGhugare19\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frbange\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_6c630a9aba04.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Roman Bange\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=rbange\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ffelixchalumeau\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_b92fa8d6d57b.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Felix Chalumeau\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=felixchalumeau\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frishabhvarshney14\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_d75feebd4e58.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Rishabh Varshney\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=rishabhvarshney14\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fzsunberg\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_7b2a7a52f30a.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Zachary Sunberg\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=zsunberg\" title=\"Code\">💻\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=zsunberg\" title=\"Documentation\">📖\u003C\u002Fa> \u003Ca href=\"#maintenance-zsunberg\" title=\"Maintenance\">🚧\u003C\u002Fa> \u003Ca href=\"#ideas-zsunberg\" title=\"Ideas, Planning, & Feedback\">🤔\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fwww.cs.cmu.edu\u002F~jlaurent\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_042005666f08.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Jonathan Laurent\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"#ideas-jonathan-laurent\" title=\"Ideas, Planning, & Feedback\">🤔\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fdrozzy\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_f3ee26a24c5c.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Andriy Drozdyuk\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=drozzy\" title=\"Documentation\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"http:\u002F\u002Fritchielee.net\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_6d6561d1f279.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Ritchie Lee\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Arcnlee\" title=\"Bug reports\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fxiruizhao\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_aced71647b12.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Xirui Zhao\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=xiruizhao\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmetab0t\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_76ee22aee55e.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Nerd\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=metab0t\" title=\"Documentation\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Falbheim\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_baed0a9051c2.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Albin Heimerson\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=albheim\" title=\"Code\">💻\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=albheim\" title=\"Documentation\">📖\u003C\u002Fa> \u003Ca href=\"#maintenance-albheim\" title=\"Maintenance\">🚧\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmichelangelo21\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_1239cfc7185a.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>michelangelo21\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Amichelangelo21\" title=\"Bug reports\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fpilgrimygy\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_3eeba20138f7.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>GuoYu Yang\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=pilgrimygy\" title=\"Documentation\">📖\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=pilgrimygy\" title=\"Code\">💻\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Apilgrimygy\" title=\"Bug reports\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FMobius1D\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_2ce5773f0dc7.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Prasidh Srikumar\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=Mobius1D\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Filancoulon\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_5945f83d8961.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Ilan Coulon\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=ilancoulon\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJinraeKim\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_97781dec7f30.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Jinrae Kim\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=JinraeKim\" title=\"Documentation\">📖\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3AJinraeKim\" title=\"Bug reports\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fluigiannelli\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_98d37dbf3a7a.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>luigiannelli\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Aluigiannelli\" title=\"Bug reports\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJBoerma\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_fdce8552cdcd.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Jacob Boerma\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=JBoerma\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"http:\u002F\u002Fgitlab.com\u002Fplut0n\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_b2589583f039.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Xavier Valcarce\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Aplu70n\" title=\"Bug reports\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fashwani-rathee.github.io\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_960f0105f5a4.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Ashwani Rathee\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=ashwani-rathee\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fjamblejoe\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_3e059845fe46.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Goran Nakerst\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=jamblejoe\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fultradian\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_5156ab5569df.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>ultradian\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=ultradian\" title=\"Documentation\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fbandism.net\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_73d65636eb8d.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Ikko Ashimine\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=eltociear\" title=\"Documentation\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002F00krishna\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_ef6c6b10ea8d.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Krishna Bhogaonker\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3A00krishna\" title=\"Bug reports\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fwww.is3.uni-koeln.de\u002Fde\u002Fteam\u002Fdoctoral-researchers\u002Fphilipp-artur-kienscherf\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_91585949c839.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Philipp A. Kienscherf\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Apkienscherf\" title=\"Bug reports\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"http:\u002F\u002Fblog.krastanov.org\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_dae791e6ffd9.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Stefan Krastanov\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=Krastanov\" title=\"Documentation\">📖\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FLaarsOman\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_e66356393a38.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>LaarsOman\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=LaarsOman\" title=\"Documentation\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fburmecia\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_330d54464c29.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Bo Lu\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=burmecia\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fpeterchen96\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_2b94529b4cc1.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Peter Chen\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=peterchen96\" title=\"Code\">💻\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=peterchen96\" title=\"Documentation\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FShuhua_Gao2\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_0110e508c8a3.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Shuhua Gao\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=ShuhuaGao\" title=\"Code\">💻\u003C\u002Fa> \u003Ca href=\"#question-ShuhuaGao\" title=\"Answering Questions\">💬\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fjohannes-fischer\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_d573aa4a2ed1.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>johannes-fischer\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=johannes-fischer\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002F3rdCore\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_6b46d72817d7.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Tom Marty\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3A3rdCore\" title=\"Bug reports\">🐛\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=3rdCore\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fbhatiaabhinav.github.io\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_1edd733a2f32.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Abhinav Bhatia\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Abhatiaabhinav\" title=\"Bug reports\">🐛\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=bhatiaabhinav\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"http:\u002F\u002Fharwiltz.github.io\u002Fabout\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_7d9da8320a6d.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Harley Wiltzer\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=harwiltz\" title=\"Code\">💻\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=harwiltz\" title=\"Documentation\">📖\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Aharwiltz\" title=\"Bug reports\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fdylan-asmar\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_8ebfa8d18675.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Dylan Asmar\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=dylan-asmar\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fandreyzhitnikov\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_2ec57dc2411d.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>andreyzhitnikov\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Aandreyzhitnikov\" title=\"Bug reports\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fkir0ul\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_63368ad18539.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Andrea PIERRÉ\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=kir0ul\" title=\"Documentation\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FMo8it\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_c470dce74200.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Mo8it\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=Mo8it\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"http:\u002F\u002Fblegat.github.io\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_68e7d15e3835.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Benoît Legat\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=blegat\" title=\"Documentation\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FHenriDeh\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_fdacbd700d80.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Henri Dehaybe\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=HenriDeh\" title=\"Code\">💻\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=HenriDeh\" title=\"Documentation\">📖\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fnplawrence.com\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_c789f162b164.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>NPLawrence\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=NPLawrence\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FbileamScheuvens\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_2293b9cb332a.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Bileam Scheuvens\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=bileamScheuvens\" title=\"Documentation\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"http:\u002F\u002Fjarbus.net\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_5c57577f2eb5.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Jarbus\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Ajarbus\" title=\"Bug reports\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ftyleringebrand\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_c4a644a52353.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>tyleringebrand\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Atyleringebrand\" title=\"Bug reports\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fbaedan\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_0e272391c75a.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>baedan\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=baedan\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fll7\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_9154a5404b38.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>ll7\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=ll7\" title=\"Documentation\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"http:\u002F\u002Fmplemay.github.io\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_86590299adb7.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Matthew LeMay\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=mplemay\" title=\"Documentation\">📖\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fludvigk\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_795253b10b67.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Ludvig Killingberg\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=ludvigk\" title=\"Code\">💻\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n\u003C!-- markdownlint-restore -->\n\u003C!-- prettier-ignore-end -->\n\n\u003C!-- ALL-CONTRIBUTORS-LIST:END -->\n\u003C!-- cSpell:enable -->\n\u003C!-- ``` -->\n\nThis project follows the [all-contributors](https:\u002F\u002Fgithub.com\u002Fall-contributors\u002Fall-contributors) specification. Contributions of any kind welcome!\n","\u003C!-- ```@raw html -->\n\u003Cdiv align=\"center\">\n  \u003Cp>\n  \u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fraw\u002Fmain\u002Fdocs\u002Fsrc\u002Fassets\u002Flogo.svg?sanitize=true\" width=\"320px\">\n  \u003C\u002Fp>\n  \n  \u003Cp>\n  \u003Ca href=\"https:\u002F\u002Fwiki.c2.com\u002F?MakeItWorkMakeItRightMakeItFast\">\"先让它工作，再让它正确，最后让它快速\"\u003C\u002Fa>\n  \u003C\u002Fp>\n  \n  \u003Cp>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Factions?query=workflow%3ACI\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fworkflows\u002FCI\u002Fbadge.svg\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fjuliahub.com\u002Fui\u002FPackages\u002FReinforcementLearning\u002F6l2TO\">\u003Cimg src=\"https:\u002F\u002Fjuliahub.com\u002Fdocs\u002FReinforcementLearning\u002Fpkgeval.svg\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fjuliahub.com\u002Fui\u002FPackages\u002FReinforcementLearning\u002F6l2TO\">\u003Cimg src=\"https:\u002F\u002Fjuliahub.com\u002Fdocs\u002FReinforcementLearning\u002Fversion.svg\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fblob\u002Fmain\u002FLICENSE.md\">\u003Cimg src=\"http:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-brightgreen.svg?style=flat\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fjulialang.org\u002Fslack\u002F\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FChat%20on%20Slack-%23reinforcement--learnin-ff69b4\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FSciML\u002FColPrac\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FColPrac-Contributor's%20Guide-blueviolet\">\u003C\u002Fa>\n  \u003C\u002Fp>\n\n\u003C\u002Fdiv>\n\u003C!-- ``` -->\n\n---\n\n[**ReinforcementLearning.jl**](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl),\n顾名思义，是 Julia 语言中用于强化学习研究的一个软件包。\n\n我们的设计原则是：\n\n- **可复用性与可扩展性**：提供精心设计的组件和接口，帮助用户实现新的算法。\n- **易于实验**：让新用户能够轻松运行基准实验、比较不同算法、评估和诊断智能体。\n- **可重复性**：从传统的表格型方法到现代深度强化学习算法，均能促进结果的可重复性。\n  \n\n## 🏹 快速入门\n\n```julia\njulia> ] add ReinforcementLearning\n\njulia> using ReinforcementLearning\n\njulia> run(\n           RandomPolicy(),\n           CartPoleEnv(),\n           StopAfterNSteps(1_000),\n           TotalRewardPerEpisode()\n       )\n```\n\n上述简单示例展示了通用强化学习实验中的四个核心组件：\n\n- **策略**。[`RandomPolicy`](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fdocs\u002Frlcore\u002F#ReinforcementLearningCore.RandomPolicy)\n  是 [`AbstractPolicy`](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fdocs\u002Frlbase\u002F#ReinforcementLearningBase.AbstractPolicy) 的最简单实例。\n  它在每一步都会随机选择一个动作。\n\n- **环境**。[`CartPoleEnv`](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fdocs\u002Frlenvs\u002F#ReinforcementLearningEnvironments.CartPoleEnv-Tuple%7B%7D)\n  是典型的 [`AbstractEnv`](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fdocs\u002Frlbase\u002F#ReinforcementLearningBase.AbstractEnv)，用于测试强化学习算法。\n\n- **停止条件**。[`StopAfterNSteps(1_000)`](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fdocs\u002Frlcore\u002F#ReinforcementLearningCore.StopAfterNSteps)\n  表示实验应在执行 `1_000` 步后停止。\n\n- **钩子**。[`TotalRewardPerEpisode`](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fdocs\u002Frlcore\u002F#ReinforcementLearningCore.TotalRewardPerEpisode)\n  结构是最常见的 [`AbstractHook`](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fdocs\u002Frlcore\u002F#ReinforcementLearningCore.AbstractHook) 之一。\n  它用于收集实验中每一集的总奖励。\n\n请查看 [教程](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fdocs\u002Ftutorial\u002F) 页面，了解如何将这四个组件组合起来解决许多有趣的问题。我们也会不定期撰写 [博客](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fblog\u002F) 来解释一些算法的实现细节。其中最推荐的是 [*ReinforcementLearning.jl 简介*](https:\u002F\u002Fjuliareinforcementlearning.org\u002Fblog\u002Fan_introduction_to_reinforcement_learning_jl_design_implementations_thoughts\u002F)，\n它详细阐述了本包的设计理念。\n\n## 🙋 为什么选择 ReinforcementLearning.jl？\n\n### 🚀 高速性能\n\n[待补充:]\n\n### 🧰 功能丰富\n\n[待补充:]\n\n## 🌲 项目结构\n\n`ReinforcementLearning.jl` 本身只是对几个其他子包的封装。它们之间的关系如下所示：\n\n\u003C!-- ```@raw html -->\n\u003Cpre>+-----------------------------------------------------------------------------------+\n|                                                                                   |\n|  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\">ReinforcementLearning.jl\u003C\u002Fa>                                                         |\n|                                                                                   |\n|      +------------------------------+                                             |\n|      | \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Ftree\u002Fmain\u002Fsrc\u002FReinforcementLearningBase\">ReinforcementLearningBase.jl\u003C\u002Fa> |                                             |\n|      +----|-------------------------+                                             |\n|           |                                                                       |\n|           |     +--------------------------------------+                          |\n|           +---->+ \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Ftree\u002Fmain\u002Fsrc\u002FReinforcementLearningEnvironments\">ReinforcementLearningEnvironments.jl\u003C\u002Fa> |                          |\n|           |     +--------------------------------------+                          |\n|           |                                                                       |\n|           |     +------------------------------+                                  |\n|           +---->+ \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Ftree\u002Fmain\u002Fsrc\u002FReinforcementLearningCore\">ReinforcementLearningCore.jl\u003C\u002Fa> |                                  |\n|                 +----|-------------------------+                                  |\n|                      |                                                            |\n|                      |     +-----------------------------+                        |\n|                      +---->+ \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Ftree\u002Fmain\u002Fsrc\u002FReinforcementLearningZoo\">ReinforcementLearningZoo.jl\u003C\u002Fa> |                        |\n|                            +----|------------------------+                        |\n|                                 |                                                 |\n|                                 |     +-------------------------------------+     |\n|                                 +---->+ \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FDistributedReinforcementLearning.jl\">DistributedReinforcementLearning.jl\u003C\u002Fa> |     |\n|                                       +-------------------------------------+     |\n|                                                                                   |\n+------|----------------------------------------------------------------------------+\n       |\n       |     +-------------------------------------+\n       +---->+ \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Ftree\u002Fmain\u002Fsrc\u002FReinforcementLearningExperiments\">ReinforcementLearningExperiments.jl\u003C\u002Fa> |\n       |     +-------------------------------------+\n       |\n       |     +----------------------------------------+\n       +---->+ \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearningAnIntroduction.jl\">ReinforcementLearningAnIntroduction.jl\u003C\u002Fa> |\n             +----------------------------------------+\n\n\u003C\u002Fpre>\n\u003C!-- ``` -->\n\n## ✋ 获取帮助\n您正在寻找关于 ReinforcementLearning.jl 的帮助吗？以下是几种获取帮助的方式：\n1. 阅读在线文档！答案很可能已经在某个示例或 API 文档中给出。请使用左上角的搜索栏进行查找。\n\u003C!-- cspell:disable-next -->\n2. 在 [Julia Slack](https:\u002F\u002Fjulialang.org\u002Fslack\u002F) 的 #reinforcement-learnin 频道与我们交流。\n3. 在 [Julia discourse](https:\u002F\u002Fdiscourse.julialang.org\u002F) 论坛的“机器学习”分类下发布问题，并使用“reinforcement-learning”作为标签。\n4. 如果遇到 ReinforcementLearning.jl 的意外行为或缺陷问题，请在 ReinforcementLearning 的 [GitHub 页面](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl) 上提交一个包含最小可复现示例和复现步骤的问题。\n\n## 🖖 支持\n`ReinforcementLearning.jl` 是一个 MIT 许可证下的开源项目，其持续开发得益于众多贡献者在业余时间的努力。然而，现代强化学习研究需要大量的计算资源，这对个人贡献者来说是难以负担的。因此，如果您或您的组织能够在一定程度上提供计算资源并希望以某种方式合作，请随时与我们联系！\n\n本包完全用 Julia 编写。如果您觉得这个包很有用，请考虑[支持 JuliaLang 组织](https:\u002F\u002Fgithub.com\u002Fsponsors\u002FJuliaLang)。❤\n\n## ✍️ 引用\n如果您在科学出版物中使用了 `ReinforcementLearning.jl`，我们非常感谢您能引用其中的 [CITATION.bib](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fblob\u002Fmain\u002FCITATION.bib) 文件。\n\n## ✨ 贡献者\n感谢以下各位优秀的贡献者（[emoji key](https:\u002F\u002Fallcontributors.org\u002Fdocs\u002Fen\u002Femoji-key)）：\n\n\u003C!-- ```@raw html -->\n\u003C!-- cSpell:disable -->\n\u003C!-- ALL-CONTRIBUTORS-LIST:START - 请勿删除或修改此部分 -->\n\u003C!-- prettier-ignore-start -->\n\u003C!-- markdownlint-disable -->\n\u003Ctable>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"http:\u002F\u002Flcn.epfl.ch\u002F~brea\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_141891678f7c.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>jbrea\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=jbrea\" title=\"代码\">💻\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=jbrea\" title=\"文档\">📖\u003C\u002Fa> \u003Ca href=\"#maintenance-jbrea\" title=\"维护\">🚧\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Ftianjun.me\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_d4860ef85a5b.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Jun Tian\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=findmyway\" title=\"代码\">💻\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=findmyway\" title=\"文档\">📖\u003C\u002Fa> \u003Ca href=\"#maintenance-findmyway\" title=\"维护\">🚧\u003C\u002Fa> \u003Ca href=\"#ideas-findmyway\" title=\"想法、规划与反馈\">🤔\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Famanbh\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_879705d44ba5.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Aman Bhatia\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=amanbh\" title=\"文档\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Favt.im\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_3320e58baa12.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Alexander Terenin\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=aterenin\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FSid-Bhatia-0\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_10b1b6ac873f.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Sid-Bhatia-0\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=Sid-Bhatia-0\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fnorci\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_d867920150fc.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>norci\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=norci\" title=\"代码\">💻\u003C\u002Fa> \u003Ca href=\"#maintenance-norci\" title=\"维护\">🚧\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fsriram13m\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_3b2a578cf47f.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Sriram\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=sriram13m\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fgpavanb1\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_6880dba73945.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Pavan B Govindaraju\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=gpavanb1\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FAlexLewandowski\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_7004ba176508.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Alex Lewandowski\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=AlexLewandowski\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FRajGhugare19\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_59b06793660d.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Raj Ghugare\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=RajGhugare19\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frbange\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_6c630a9aba04.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Roman Bange\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=rbange\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ffelixchalumeau\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_b92fa8d6d57b.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Felix Chalumeau\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=felixchalumeau\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Frishabhvarshney14\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_d75feebd4e58.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Rishabh Varshney\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=rishabhvarshney14\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fzsunberg\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_7b2a7a52f30a.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Zachary Sunberg\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=zsunberg\" title=\"代码\">💻\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=zsunberg\" title=\"文档\">📖\u003C\u002Fa> \u003Ca href=\"#maintenance-zsunberg\" title=\"维护\">🚧\u003C\u002Fa> \u003Ca href=\"#ideas-zsunberg\" title=\"想法、规划与反馈\">🤔\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fwww.cs.cmu.edu\u002F~jlaurent\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_042005666f08.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Jonathan Laurent\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"#ideas-jonathan-laurent\" title=\"想法、规划与反馈\">🤔\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fdrozzy\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_f3ee26a24c5c.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Andriy Drozdyuk\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=drozzy\" title=\"文档\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"http:\u002F\u002Fritchielee.net\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_6d6561d1f279.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Ritchie Lee\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Arcnlee\" title=\"Bug报告\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fxiruizhao\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_aced71647b12.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Xirui Zhao\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=xiruizhao\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmetab0t\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_76ee22aee55e.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Nerd\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=metab0t\" title=\"文档\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Falbheim\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_baed0a9051c2.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Albin Heimerson\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=albheim\" title=\"代码\">💻\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=albheim\" title=\"文档\">📖\u003C\u002Fa> \u003Ca href=\"#maintenance-albheim\" title=\"维护\">🚧\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmichelangelo21\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_1239cfc7185a.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>michelangelo21\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Amichelangelo21\" title=\"Bug报告\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fpilgrimygy\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_3eeba20138f7.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>GuoYu Yang\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=pilgrimygy\" title=\"文档\">📖\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=pilgrimygy\" title=\"代码\">💻\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Apilgrimygy\" title=\"Bug报告\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FMobius1D\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_2ce5773f0dc7.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Prasidh Srikumar\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=Mobius1D\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Filancoulon\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_5945f83d8961.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Ilan Coulon\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=ilancoulon\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJinraeKim\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_97781dec7f30.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Jinrae Kim\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=JinraeKim\" title=\"文档\">📖\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3AJinraeKim\" title=\"Bug报告\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fluigiannelli\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_98d37dbf3a7a.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>luigiannelli\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Aluigiannelli\" title=\"Bug报告\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJBoerma\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_fdce8552cdcd.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Jacob Boerma\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=JBoerma\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"http:\u002F\u002Fgitlab.com\u002Fplut0n\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_b2589583f039.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Xavier Valcarce\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Aplu70n\" title=\"Bug报告\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fashwani-rathee.github.io\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_960f0105f5a4.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Ashwani Rathee\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=ashwani-rathee\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fjamblejoe\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_3e059845fe46.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Goran Nakerst\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=jamblejoe\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fultradian\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_5156ab5569df.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>ultradian\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=ultradian\" title=\"文档\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fbandism.net\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_73d65636eb8d.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Ikko Ashimine\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=eltociear\" title=\"文档\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002F00krishna\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_ef6c6b10ea8d.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Krishna Bhogaonker\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3A00krishna\" title=\"Bug报告\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fwww.is3.uni-koeln.de\u002Fde\u002Fteam\u002Fdoctoral-researchers\u002Fphilipp-artur-kienscherf\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_91585949c839.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Philipp A. Kienscherf\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Apkienscherf\" title=\"Bug报告\">🐛\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"http:\u002F\u002Fblog.krastanov.org\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_dae791e6ffd9.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Stefan Krastanov\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=Krastanov\" title=\"文档\">📖\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FLaarsOman\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_e66356393a38.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>LaarsOman\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=LaarsOman\" title=\"文档\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fburmecia\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_330d54464c29.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Bo Lu\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=burmecia\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fpeterchen96\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_2b94529b4cc1.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Peter Chen\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=peterchen96\" title=\"代码\">💻\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=peterchen96\" title=\"文档\">📖\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fwww.researchgate.net\u002Fprofile\u002FShuhua_Gao2\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_0110e508c8a3.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Shuhua Gao\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=ShuhuaGao\" title=\"代码\">💻\u003C\u002Fa> \u003Ca href=\"#question-ShuhuaGao\" title=\"回答问题\">💬\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fjohannes-fischer\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_d573aa4a2ed1.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>johannes-fischer\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=johannes-fischer\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002F3rdCore\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_6b46d72817d7.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Tom Marty\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3A3rdCore\" title=\"Bug报告\">🐛\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=3rdCore\" title=\"代码\">💻\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fbhatiaabhinav.github.io\u002F\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_1edd733a2f32.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Abhinav Bhatia\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Abhatiaabhinav\" title=\"Bug报告\">……\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=bhatiaabhinav\" title=\"代码\">……\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"http:\u002F\u002Fharwiltz.github.io\u002Fabout\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_7d9da8320a6d.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Harley Wiltzer\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=harwiltz\" title=\"代码\">……\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=harwiltz\" title=\"文档\">……\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Aharwiltz\" title=\"Bug报告\">……\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fdylan-asmar\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_8ebfa8d18675.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Dylan Asmar\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=dylan-asmar\" title=\"代码\">……\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fandreyzhitnikov\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_2ec57dc2411d.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>andreyzhitnikov\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Aandreyzhitnikov\" title=\"Bug报告\">……\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fkir0ul\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_63368ad18539.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Andrea PIERRÉ\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=kir0ul\" title=\"文档\">……\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FMo8it\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_c470dce74200.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Mo8it\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=Mo8it\" title=\"代码\">……\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FBenoît Legat\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_68e7d15e3835.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Benoît Legat\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=blegat\" title=\"文档\">……\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FHenriDeh\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_fdacbd700d80.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Henri Dehaybe\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=HenriDeh\" title=\"代码\">……\u003C\u002Fa> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=HenriDeh\" title=\"文档\">……\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fnplawrence.com\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_c789f162b164.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>NPLawrence\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=NPLawrence\" title=\"代码\">……\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FbileamScheuvens\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_2293b9cb332a.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Bileam Scheuvens\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=bileamScheuvens\" title=\"文档\">……\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"http:\u002F\u002Fjarbus.net\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_5c57577f2eb5.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Jarbus\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Ajarbus\" title=\"Bug报告\">……\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ftyleringebrand\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_c4a644a52353.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>tyleringebrand\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fissues?q=author%3Atyleringebrand\" title=\"Bug报告\">……\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fbaedan\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_0e272391c75a.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>baedan\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=baedan\" title=\"代码\">……\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fll7\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_9154a5404b38.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>ll7\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=ll7\" title=\"文档\">……\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmplemay\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_86590299adb7.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Matthew LeMay\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=mplemay\" title=\"文档\">……\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fludvigk\">\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_readme_795253b10b67.png\" width=\"100px;\" alt=\"\"\u002F>\u003Cbr \u002F>\u003Csub>\u003Cb>Ludvig Killingberg\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa\u003Cbr \u002F>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcommits?author=ludvigk\" title=\"代码\">……\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n\u003C!-- markdownlint-restore -->\n\u003C!-- prettier-ignore-end -->\n\n\u003C!-- ALL-CONTRIBUTORS-LIST:END -->\n\u003C!-- cSpell:enable -->\n\u003C!-- ``` -->\n\n本项目遵循 [all-contributors](https:\u002F\u002Fgithub.com\u002Fall-contributors\u002Fall-contributors) 规范。欢迎任何形式的贡献！","# ReinforcementLearning.jl 快速上手指南\n\n## 环境准备\n\n在开始之前，请确保您的开发环境满足以下要求：\n\n*   **操作系统**：Windows、macOS 或 Linux。\n*   **Julia 版本**：建议安装最新稳定版 Julia（1.6 或更高版本）。\n    *   下载地址：[https:\u002F\u002Fjulialang.org\u002Fdownloads\u002F](https:\u002F\u002Fjulialang.org\u002Fdownloads\u002F)\n    *   *国内加速*：中国用户可访问清华源镜像下载：[https:\u002F\u002Fmirrors.tuna.tsinghua.edu.cn\u002Fjulia-releases\u002F](https:\u002F\u002Fmirrors.tuna.tsinghua.edu.cn\u002Fjulia-releases\u002F)\n*   **前置依赖**：无需额外安装 Python 或其他深度学习框架，本库纯 Julia 编写。\n\n> **提示**：为了获得更快的包下载速度，建议在首次启动 Julia 时配置国内镜像源。在 Julia REPL 中执行以下命令设置清华源：\n> ```julia\n> import Pkg\n> Pkg.Registry.add(Pkg.RegistrySpec(url=\"https:\u002F\u002Fmirrors.tuna.tsinghua.edu.cn\u002Fgit\u002Fjulia\u002FGeneral.git\"))\n> ENV[\"JULIA_PKG_SERVER\"] = \"https:\u002F\u002Fmirrors.tuna.tsinghua.edu.cn\u002Fjulia\"\n> ```\n\n## 安装步骤\n\n启动 Julia REPL，进入包管理模式（按 `]` 键），然后运行以下命令安装核心包：\n\n```julia\njulia> ] add ReinforcementLearning\n```\n\n安装完成后，退出包管理模式（按 Backspace 键），并在代码中引入该包：\n\n```julia\njulia> using ReinforcementLearning\n```\n\n## 基本使用\n\n`ReinforcementLearning.jl` 的核心设计理念是将实验拆解为四个关键组件：**策略 (Policy)**、**环境 (Environment)**、**停止条件 (Stop Condition)** 和 **钩子 (Hook)**。\n\n以下是一个最简示例，展示如何让一个随机策略智能体在经典的“倒立摆”环境中运行 1000 步，并记录每集的总奖励：\n\n```julia\njulia> run(\n           RandomPolicy(),\n           CartPoleEnv(),\n           StopAfterNSteps(1_000),\n           TotalRewardPerEpisode()\n       )\n```\n\n### 代码解析\n\n*   **`RandomPolicy()`**: 最简单的策略，每一步随机生成动作。它是 `AbstractPolicy` 的实例。\n*   **`CartPoleEnv()`**: 经典的强化学习测试环境（倒立摆），实现了 `AbstractEnv` 接口。\n*   **`StopAfterNSteps(1_000)`**: 设定实验停止条件，即在运行 1000 步后自动结束。\n*   **`TotalRewardPerEpisode()`**: 一个常用的钩子（Hook），用于收集并记录每个回合（Episode）的累计奖励。\n\n您可以基于此模板，替换不同的策略（如 DQN、PPO 等）和环境，快速构建和复现各种强化学习实验。更多高级用法请参考官方教程。","某机器人实验室的研究团队正在开发一套自适应机械臂控制系统，需要通过强化学习让机械臂在动态环境中快速学会抓取不同形状的物体。\n\n### 没有 ReinforcementLearning.jl 时\n- 研究人员需从零搭建实验框架，手动编写环境交互、策略更新和数据记录代码，耗时数周且容易出错。\n- 尝试对比不同算法（如 DQN 与 PPO）时，因缺乏统一接口，每次切换都需重构大量底层逻辑，实验效率极低。\n- 复现经典论文结果困难，由于缺少标准化的组件和基准测试环境，难以验证算法实现的正确性。\n- 调试过程中难以实时监控每轮训练的奖励变化，往往要等到训练结束才能发现策略失效，浪费大量计算资源。\n\n### 使用 ReinforcementLearning.jl 后\n- 利用预置的 `CartPoleEnv` 等标准环境和 `AbstractPolicy` 接口，团队仅用几行代码即可启动基准实验，将原型开发时间从数周缩短至几天。\n- 借助高度模块化的设计，只需替换策略组件（如将 `RandomPolicy` 换为深度策略）即可无缝切换算法，轻松完成多算法性能对比。\n- 依托包内提供的从表格方法到深度强化学习的全套可复现组件，团队能迅速对齐学术界最新成果，确保实验结果的可靠性。\n- 通过内置的 `TotalRewardPerEpisode` 等钩子（Hook），实时收集并可视化每集奖励，帮助研究者即时诊断问题并调整超参数。\n\nReinforcementLearning.jl 通过标准化组件和灵活架构，让研究人员从繁琐的工程实现中解放出来，专注于核心算法的创新与优化。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FJuliaReinforcementLearning_ReinforcementLearning.jl_067da8dd.png","JuliaReinforcementLearning","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FJuliaReinforcementLearning_669c9c01.png","A collection of tools for reinforcement learning research in Julia",null,"https:\u002F\u002Fjuliareinforcementlearning.org\u002F","https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning",[79,83],{"name":80,"color":81,"percentage":82},"Julia","#a270ba",100,{"name":84,"color":85,"percentage":86},"Dockerfile","#384d54",0,652,107,"2026-04-12T03:05:53","NOASSERTION","未说明",{"notes":93,"python":94,"dependencies":95},"该工具是基于 Julia 语言开发的强化学习包，非 Python 项目。安装需先安装 Julia 环境，然后通过 Julia 包管理器添加 'ReinforcementLearning'。具体子模块包括基础接口、环境、核心算法及算法库等。","不适用 (基于 Julia 语言)",[80,96,97,98,99],"ReinforcementLearningBase.jl","ReinforcementLearningEnvironments.jl","ReinforcementLearningCore.jl","ReinforcementLearningZoo.jl",[14],[102,103,104,105,106],"julia","reinforcement-learning","machine-learning","deep-reinforcement-learning","deep-q-network","2026-03-27T02:49:30.150509","2026-04-17T08:24:24.733178",[],[111,116,121,126,131,136,141,146,151,156,161,166,171,176,181,186,191,196,201,206],{"id":112,"version":113,"summary_zh":114,"released_at":115},297368,"ReinforcementLearningCore-v0.15.5","## 强化学习核心 强化学习核心-v0.15.5\n\n[自强化学习核心-v0.15.4 以来的差异](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcompare\u002FReinforcementLearningCore-v0.15.4...ReinforcementLearningCore-v0.15.5)\n\n\n**已合并的拉取请求：**\n- 将 UnicodePlots 移至扩展 (#1088) (@jeremiahpslewis)\n- 将 RLCore 升级至 v0.15.5 (#1089) (@jeremiahpslewis)","2025-01-13T13:21:40",{"id":117,"version":118,"summary_zh":119,"released_at":120},297369,"ReinforcementLearningFarm-v0.0.3","## 强化学习农场 强化学习农场-v0.0.3\n\n\n\n**已合并的拉取请求：**\n- 修复弃用警告 (#10) (@femtocleaner[bot])\n- 实现带参数类型的 ε-贪心策略 (#12) (@jbrea)\n- 改进文档 (#13) (@jbrea)\n- 重构策略 (#15) (@jbrea)\n- 添加 ReinforcementLearningBase 作为依赖项 (#16) (@jbrea)\n- 修复示例 (#18) (@jbrea)\n- 重构现有组件 (#26) (@findmyway)\n- 优先级 DQN (#29) (@findmyway)\n- 添加双 DQN (#30) (@findmyway)\n- 添加 Rainbow (#31) (@findmyway)\n- 在 ReinforcementLearningEnvironments.jl 中使用新 API (#33) (@findmyway)\n- 修复 bug 并简化 API (#34) (@findmyway)\n- 将 Tracker.jl 切换到 Zygote.jl (#37) (@findmyway)\n- 同时支持 Knet 和 Flux（配合 Zygote）(#38) (@findmyway)\n- 添加文档 (#39) (@findmyway)\n- 导出 AbstractActionSelector 并添加更多注释 (#42) (@findmyway)\n- 重构缓冲区 (#45) (@findmyway)\n- 修复文档中的示例并更新示例 (#46) (@findmyway)\n- 修复 Rainbow 中的一个性能问题 (#47) (@findmyway)\n- 更新依赖项 (#48) (@findmyway)\n- 更新依赖项和文档 (#49) (@findmyway)\n- 更新 circular_array_buffer 的基准测试 (#50) (@findmyway)\n- 安装 TagBot 作为 GitHub Action (#53) (@JuliaTagBot)\n- 清理代码 (#54) (@findmyway)\n- 添加兼容性条目 (#55) (@findmyway)\n- CompatHelper：为“Reexport”添加版本“0.2”的新兼容性条目 (#56) (@github-actions[bot])\n- 在 Travis 中添加文档阶段 (#57) (@findmyway)\n- 在 Travis 中添加文档 (#58) (@findmyway)\n- 修复 docs\u002Fsrc\u002Findex.md 中的链接 (#60) (@amanbh)\n- 更新文档 (#61) (@findmyway)\n- 更新 README.md 和网站链接 (#70) (@findmyway)\n- 更新依赖项 (#78) (@findmyway)\n- MassInstallAction：在此仓库安装 CompatHelper 工作流 (#99) (@findmyway)\n- CompatHelper：将“Reexport”的兼容性版本提升至“1.0” (#172) (@github-actions[bot])\n- 更新依赖项 (#177) (@findmyway)\n- 添加 Dockerfile (#187) (@findmyway)\n- 更新自述文件 (#188) (@findmyway)\n- 文档：将 findmyway 添加为贡献者 (#189) (@allcontributors[bot])\n- 文档：将 drozzy 添加为贡献者 (#195) (@allcontributors[bot])\n- 文档：将 rcnlee 添加为贡献者 (#199) (@allcontributors[bot])\n- 文档：将 norci 添加为贡献者 (#200) (@allcontributors[bot])\n- 文档：将 xiruizhao 添加为贡献者 (#203) (@allcontributors[bot])\n- 文档：将 metab0t 添加为贡献者 (#204) (@allcontributors[bot])\n- 文档：将 albheim 添加为贡献者 (#207) (@allcontributors[bot])\n- 文档：将 michelangelo21 添加为贡献者 (#214) (@allcontributors[bot])\n- 文档：将 pilgrimygy 添加为贡献者 (#216) (@allcontributors[bot])\n- 文档：将 Mobius1D 添加为贡献者 (#218) (@allcontributors[bot])\n- 文档：将 ilancoulon 添加为贡献者 (#224) (@allcontributors[bot])\n- 文档：将 pilgrimygy 添加为贡献者 (#230) (@allcontributors[bot])\n- 文档：将 JinraeKim 添加为贡献者 (#243) (@allcontributors[bot])\n- 准备 v0.9 版本 (#252) (@findmyway)\n- 文档：将 luigiannelli 添加为贡献者 (#254) (@allcontributors[bot])\n- 文档：将 JBoerma 添加为贡献者 (#255) (@allc","2024-12-18T10:22:04",{"id":122,"version":123,"summary_zh":124,"released_at":125},297370,"ReinforcementLearningCore-v0.15.4","## 强化学习核心 强化学习核心-v0.15.4\n\n[与 ReinforcementLearningCore-v0.15.3 的差异](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcompare\u002FReinforcementLearningCore-v0.15.3...ReinforcementLearningCore-v0.15.4)\n\n\n**已合并的拉取请求：**\n- 修复 RLEnvs 版本 (#1076) (@jeremiahpslewis)\n- 修复 TagBot (#1077) (@jeremiahpslewis)\n- 修复文档首页 (#1082) (@michalrzak)\n- Jpsl\u002F更新 Flux (#1086) (@jeremiahpslewis)","2024-12-18T00:07:12",{"id":127,"version":128,"summary_zh":129,"released_at":130},297371,"ReinforcementLearningEnvironments-v0.9.1","## 强化学习环境 强化学习环境-v0.9.1\n\n[自强化学习环境-v0.9.0 以来的差异](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcompare\u002FReinforcementLearningEnvironments-v0.9.0...ReinforcementLearningEnvironments-v0.9.1)\n\n\n**已合并的拉取请求：**\n- 添加缺失的 Flux 兼容性 (#1059) (@jeremiahpslewis)\n- 修复文档\u002F网站构建问题 (#1064) (@jeremiahpslewis)\n- 修正单摆的 x-y 坐标 (#1065) (@HenriDeh)\n- 使 QBasedPolicy 对所有 AbstractLearner 类型通用 (#1069) (@dharux)\n- 修复多人模式下的钩子问题 (#1071) (@jeremiahpslewis)\n- 修复文档构建错误 (#1072) (@jeremiahpslewis)\n- 升级 rlcore 版本 (#1073) (@jeremiahpslewis)\n- 使 `FluxApproximator` 能与 `QBasedPolicy` 配合使用 (#1075) (@jeremiahpslewis)\n- 修复 RLEnvs 版本问题 (#1076) (@jeremiahpslewis)\n\n**已关闭的问题：**\n- 下一版本计划 (v0.11) (#614)\n- 包稳定化计划 (#792)\n- test\u002Fruntests.jl 文件为空 (+ 架构讨论) (#843)\n- policy(env) 返回无合法动作 -inf 初始化的 Q 表 (#852)\n- 将 CI 重构为每个包单独的工作流 (并为每个包设置独立的 codecov 项目) (#869)\n- 为未重构的策略添加弃用警告 (#892)\n- 向量化环境 (#908)\n- 加载 Gym 环境 (#912)\n- 使用 MaskedPPOTrajectory 的 PPO (#917)\n- 开发模式无法正常工作 (#918)\n- TD3 策略无法处理具有多维动作空间的环境 (#951)\n- 拆分核心包 (#960)\n- 实验失败 (#982)\n- 使教程中的 TotalRewardPerEpisode 与 run 调用中的停止条件不同步，从而破坏了教程 (#1000)\n- 将算法迁移到 RLFarm (#1028)\n- 更新 Buildkite 脚本以支持 GPU 测试，并使其与子包兼容 (#1030)\n- 网站：强化学习实用入门：未作介绍，源代码损坏 (#1036)\n- ElasticArraySARTSTraces 未能正确记录 `MountainCarEnv()` 的轨迹 (#1067)\n- 算法实现 (#1070)\n- 没有匹配 ArrayProductDomain 的 iterate 方法 (#1074)","2024-05-13T14:08:09",{"id":132,"version":133,"summary_zh":134,"released_at":135},297372,"ReinforcementLearningCore-v0.15.3","## 强化学习核心 强化学习核心-v0.15.3\n\n[与 ReinforcementLearningCore-v0.15.2 相比的差异](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcompare\u002FReinforcementLearningCore-v0.15.2...ReinforcementLearningCore-v0.15.3)\n\n\n**已合并的拉取请求：**\n- 使 `FluxApproximator` 能与 `QBasedPolicy` 配合使用 (#1075) (@jeremiahpslewis)","2024-05-13T11:52:17",{"id":137,"version":138,"summary_zh":139,"released_at":140},297373,"ReinforcementLearningBase-v0.13.1","## ReinforcementLearningBase ReinforcementLearningBase-v0.13.1\n\n[与 ReinforcementLearningBase-v0.13.0 的差异](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcompare\u002FReinforcementLearningBase-v0.13.0...ReinforcementLearningBase-v0.13.1)\n\n\n**已合并的拉取请求：**\n- 添加缺失的 Flux 兼容性 (#1059) (@jeremiahpslewis)\n- 修复文档\u002F网站构建问题 (#1064) (@jeremiahpslewis)\n- 纠正 Pendulum 摆锤的 x-y 坐标 (#1065) (@HenriDeh)\n- 使 QBasedPolicy 对所有 AbstractLearner 类型通用 (#1069) (@dharux)\n- 修复多人模式下的钩子问题 (#1071) (@jeremiahpslewis)\n- 修复文档构建错误 (#1072) (@jeremiahpslewis)\n- 升级 rlcore 版本 (#1073) (@jeremiahpslewis)\n- 使 `FluxApproximator` 能够与 `QBasedPolicy` 配合使用 (#1075) (@jeremiahpslewis)\n\n**已关闭的问题：**\n- 下一版本计划 (v0.11) (#614)\n- 包稳定化计划 (#792)\n- test\u002Fruntests.jl 文件为空 (+ 架构讨论) (#843)\n- policy(env) 返回无合法动作 -inf 初始化的 Q 表 (#852)\n- 将 CI 重构为每个包单独的工作流 (并为每个包设置独立的 codecov 项目) (#869)\n- 为未重构的策略添加弃用警告 (#892)\n- 向量化环境 (#908)\n- 加载 Gym 环境 (#912)\n- 使用 MaskedPPOTrajectory 的 PPO (#917)\n- 开发模式无法正常工作 (#918)\n- TD3 策略无法处理具有多维动作空间的环境 (#951)\n- 核心包拆分 (#960)\n- 实验失败 (#982)\n- 使教程中的 TotalRewardPerEpisode 与 `run` 调用中的停止条件不同步，从而破坏了教程 (#1000)\n- 将算法迁移到 RLFarm (#1028)\n- 更新 Buildkite 脚本以支持 GPU 测试，并使其与子包兼容 (#1030)\n- 网站：RL 实用入门：未进行介绍，源代码存在缺陷 (#1036)\n- ElasticArraySARTSTraces 无法正确记录 `MountainCarEnv()` 的轨迹 (#1067)\n- 算法实现 (#1070)","2024-05-13T11:52:10",{"id":142,"version":143,"summary_zh":144,"released_at":145},297374,"ReinforcementLearningCore-v0.15.2","## 强化学习核心 强化学习核心-v0.15.2\n\n[自强化学习核心-v0.15.1 以来的差异](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcompare\u002FReinforcementLearningCore-v0.15.1...ReinforcementLearningCore-v0.15.2)\n\n\n**已合并的拉取请求：**\n- 使基于Q值的策略对抽象学习器通用 (#1069) (@dharux)\n- 提升rlcore版本 (#1073) (@jeremiahpslewis)","2024-04-18T12:26:04",{"id":147,"version":148,"summary_zh":149,"released_at":150},297375,"ReinforcementLearningCore-v0.15.1","## ReinforcementLearningCore ReinforcementLearningCore-v0.15.1\n\n[与 ReinforcementLearningCore-v0.15.0 的差异](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcompare\u002FReinforcementLearningCore-v0.15.0...ReinforcementLearningCore-v0.15.1)\n\n\n**已合并的拉取请求：**\n- 添加缺失的 Flux 兼容性 (#1059) (@jeremiahpslewis)\n- 修复文档\u002F网站构建问题 (#1064) (@jeremiahpslewis)\n- 纠正 Pendulum 摆的 x-y 坐标 (#1065) (@HenriDeh)\n- 修复多玩家情况下的钩子 (#1071) (@jeremiahpslewis)\n- 修复文档构建错误 (#1072) (@jeremiahpslewis)\n\n**已关闭的问题：**\n- 下一版本计划 (v0.11) (#614)\n- 包稳定化计划 (#792)\n- test\u002Fruntests.jl 文件为空 (+ 架构讨论) (#843)\n- policy(env) 返回无合法动作 -inf 初始化的 Q 表 (#852)\n- 将 CI 重构为每个包单独的工作流（并为每个包设置单独的 Codecov 项目）(#869)\n- 为未重构的策略添加弃用警告 (#892)\n- 向量化环境 (#908)\n- 加载 Gym 环境 (#912)\n- 使用 MaskedPPOTrajectory 的 PPO (#917)\n- 开发模式无法正常工作 (#918)\n- TD3 策略无法处理具有多维动作空间的环境 (#951)\n- 拆分核心包 (#960)\n- 实验失败 (#982)\n- 使教程失效：将 TotalRewardPerEpisode 与 `run` 调用中的停止条件不同步 (#1000)\n- 将算法迁移至 RLFarm (#1028)\n- 更新 Buildkite 脚本以支持 GPU 测试，并使其与子包兼容 (#1030)\n- 网站：《强化学习实用入门》：未作介绍，源代码损坏 (#1036)\n- ElasticArraySARTSTraces 无法正确记录 `MountainCarEnv()` 的轨迹 (#1067)\n- 算法实现 (#1070)","2024-04-18T10:12:20",{"id":152,"version":153,"summary_zh":154,"released_at":155},297376,"v0.11.0","## 强化学习 v0.11.0\n\n[与 v0.10.2 的差异](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcompare\u002Fv0.10.2...v0.11.0)\n\n\n**已合并的拉取请求：**\n- 重新启用 RLExperiments 的部分测试 (#790) (@jeremiahpslewis)\n- 从 Experiments 中移除 RL.jl 依赖 (#795) (@jeremiahpslewis)\n- 修复 RLBase 的兼容性问题 (#796) (@jeremiahpslewis)\n- 修正 RLCore 版本，为版本号提升做准备 (#797) (@jeremiahpslewis)\n- 添加重导出兼容性 (#798) (@jeremiahpslewis)\n- 提升兼容性辅助工具版本 (#799) (@jeremiahpslewis)\n- 修复 RLEnvironments 对 IntervalSets 的兼容性问题 (#800) (@jeremiahpslewis)\n- 为发布提升 RLZoo.jl 版本号 (#815) (@jeremiahpslewis)\n- 修复 RLExperiments 的兼容性问题 (#816) (@jeremiahpslewis)\n- 扩展 RLZoo 的兼容性范围 (#817) (@jeremiahpslewis)\n- 提升 RLExperiments 版本，要求使用 0.11 版本 (#818) (@jeremiahpslewis)\n- 在 RLExperiments 中将 ReinforcementLearningZoo.jl 锁定至 0.6 版本 (#819) (@jeremiahpslewis)\n- 从 CompatHelper 中移除 RL.jl（直至重构完成）(#824) (@jeremiahpslewis)\n- 提升 GitHub Actions 缓存版本 (#825) (@jeremiahpslewis)\n- 针对 RandomWalk \u002F RandomPolicy 进行基础的内存分配修复 (#827) (@jeremiahpslewis)\n- 提升 CI.yml 中 GitHub Actions 的版本 (#828) (@jeremiahpslewis)\n- 增加测试，提升 RewardsPerEpisode 的性能 (#829) (@jeremiahpslewis)\n- 对 TotalBatchRewardPerEpisode 进行重构并增加测试 (#830) (@jeremiahpslewis)\n- 为 TimePerStep 增加测试并进行性能优化 (#831) (@jeremiahpslewis)\n- 为 DoEveryNStep 增加测试，并进行性能调整 (#832) (@jeremiahpslewis)\n- 增加 DoOnExit 测试 (#833) (@jeremiahpslewis)\n- 扩展 PR 模板 (#835) (@jeremiahpslewis)\n- 修正分支名称（master → main）(#837) (@jeremiahpslewis)\n- 为剩余的钩子函数添加 test_noop! 测试 (#840) (@jeremiahpslewis)\n- 使 TimePerStep 测试更加健壮 (#841) (@jeremiahpslewis)\n- 重新启用文档生成 (#842) (@jeremiahpslewis)\n- 在 tips.md 中添加 activate_devmode!() 的说明 (#845) (@jeremiahpslewis)\n- 将 RL.jl 的兼容性提升至 0.11.0-dev 版本 (#846) (@jeremiahpslewis)\n- 为代理添加关键字参数 (#847) (@HenriDeh)\n- 高斯网络的重构及测试 (#849) (@HenriDeh)\n- 代理重构 (#850) (@jeremiahpslewis)\n- 提升 RLCore 版本 (#851) (@jeremiahpslewis)\n- 在 CI 中加入 Codecov (#854) (@HenriDeh)\n- 修复 MPO 中的一个拼写错误 (#855) (@HenriDeh)\n- DoEvery 不应在 t = 1 时触发 (#856) (@HenriDeh)\n- 更新 CI 的 Julia 版本 (#857) (@jeremiahpslewis)\n- 调整 CI 以检查依赖项的变化 (#858) (@HenriDeh)\n- CompatHelper：为 ReinforcementLearningCore 包提升 FillArrays 的兼容性至 1 版本（保留现有兼容性）(#859) (@github-actions[bot])\n- 多智能体提案 (#861) (@jeremiahpslewis)\n- CompatHelper：为 ReinforcementLearningEnvironments 包新增 ReinforcementLearningCore 0.9 版本的兼容条目（保留现有兼容性）(#865) (@github-actions[bot])\n- 多人游戏修复（清理错误）(#867) (@jeremiahpslewis)\n- 在首页增加关于如何获取强化学习帮助的部分 (#868) (@LooseTerrifyingSpaceMonkey)\n- 提升 StatsBase 的兼容性 (#873) (@jeremiahpslewis)\n- ComposedHooks 和 MultiHook 的修复 (#874) (@j","2024-03-26T18:29:02",{"id":157,"version":158,"summary_zh":159,"released_at":160},297377,"ReinforcementLearningEnvironments-v0.9.0","## 强化学习环境 强化学习环境-v0.9.0\n\n[自强化学习环境-v0.8.8以来的差异](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcompare\u002FReinforcementLearningEnvironments-v0.8.8...ReinforcementLearningEnvironments-v0.9.0)\n\n\n**已合并的拉取请求：**\n- 将RLZoo升级至v0.8 (#1031) (@jeremiahpslewis)\n- 修复RLZoo版本问题 (#1032) (@jeremiahpslewis)\n- 移除开发模式，准备发布RL.jl v0.11 (#1035) (@jeremiahpslewis)\n- 更新文档脚本以适应新的‘limited’版RL.jl发布 (#1038) (@jeremiahpslewis)\n- 表格近似器修复（v0.11变更前）(#1040) (@jeremiahpslewis)\n- 在CI中用RLFarm替换RLZoo，并移除RLExperiments (#1041) (@jeremiahpslewis)\n- 针对单体仓库的Buildkite调整 (#1042) (@jeremiahpslewis)\n- 移除已归档项目 (#1043) (@jeremiahpslewis)\n- 在移除RLExperiment后简化实验代码 (#1044) (@jeremiahpslewis)\n- 修复代码覆盖率范围，使其忽略测试目录 (#1045) (@jeremiahpslewis)\n- 修复重置和停止条件 (#1046) (@jeremiahpslewis)\n- 移除Functors，改用Flux.@layer (#1048) (@jeremiahpslewis)\n- 修复命名一致性，并添加缺失的钩子测试 (#1049) (@jeremiahpslewis)\n- 将SARS tdlearning重新加入库中 (#1050) (@jeremiahpslewis)\n- 更新FluxModelApproximator引用为FluxApproximator (#1051) (@jeremiahpslewis)\n- Epsilon Speedy Explorer (#1052) (@jeremiahpslewis)\n- 添加每集最后N次的总奖励钩子 (#1053) (@jeremiahpslewis)\n- 修复多玩家游戏的abstract_learner (#1054) (@jeremiahpslewis)\n- 更新版本号 (#1055) (@jeremiahpslewis)\n- 为v0.11版本更新文档 (#1056) (@jeremiahpslewis)\n- 更新Katex版本，修复漏洞 (#1058) (@jeremiahpslewis)\n\n**已关闭的问题：**\n- 简单的强化学习示例崩溃 (#1034)\n- 网站：“如何实现新算法”内容已过时 (#1037)\n- 审查TabularApproximator (#1039)","2024-03-26T17:53:11",{"id":162,"version":163,"summary_zh":164,"released_at":165},297378,"ReinforcementLearningCore-v0.15.0","## ReinforcementLearningCore ReinforcementLearningCore-v0.15.0\n\n[Diff since ReinforcementLearningCore-v0.14.0](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcompare\u002FReinforcementLearningCore-v0.14.0...ReinforcementLearningCore-v0.15.0)\n\n\n**Merged pull requests:**\n- Bump RLZoo to v0.8 (#1031) (@jeremiahpslewis)\n- Fix RLZoo version (#1032) (@jeremiahpslewis)\n- Drop devmode, prepare RL.jl v0.11 for release (#1035) (@jeremiahpslewis)\n- Update docs script for new 'limited' RL.jl release (#1038) (@jeremiahpslewis)\n- Tabular Approximator fixes (pre v0.11 changes) (#1040) (@jeremiahpslewis)\n- Swap RLZoo for RLFarm in CI, drop RLExperiments (#1041) (@jeremiahpslewis)\n- Buildkite tweaks for monorepo (#1042) (@jeremiahpslewis)\n- Drop archived projects (#1043) (@jeremiahpslewis)\n- Simplify Experiment code after dropping RLExperiment (#1044) (@jeremiahpslewis)\n- Fix code coverage scope so it ignores test dir (#1045) (@jeremiahpslewis)\n- Fix reset and stop conditions (#1046) (@jeremiahpslewis)\n- Drop Functors and use Flux.@layer (#1048) (@jeremiahpslewis)\n- Fix naming consistency and add missing hook tests (#1049) (@jeremiahpslewis)\n- Add SARS tdlearning back to lib (#1050) (@jeremiahpslewis)\n- Update FluxModelApproximator references to FluxApproximator (#1051) (@jeremiahpslewis)\n- Epsilon Speedy Explorer (#1052) (@jeremiahpslewis)\n- Add TotalRewardPerEpisodeLastN hook (#1053) (@jeremiahpslewis)\n- Fix abstract_learner for multiplayer games (#1054) (@jeremiahpslewis)\n- Update versions (#1055) (@jeremiahpslewis)\n- Update Docs for v0.11 release (#1056) (@jeremiahpslewis)\n- Update Katex version, fix vulnerability (#1058) (@jeremiahpslewis)\n\n**Closed issues:**\n- Simple ReinforcementLearning example crashes (#1034)\n- Website: How do implement a new algorithm is outdated  (#1037)\n- Review TabularApproximator (#1039)","2024-03-26T17:37:15",{"id":167,"version":168,"summary_zh":169,"released_at":170},297379,"ReinforcementLearningBase-v0.13.0","## ReinforcementLearningBase ReinforcementLearningBase-v0.13.0\n\n[Diff since ReinforcementLearningBase-v0.12.2](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcompare\u002FReinforcementLearningBase-v0.12.2...ReinforcementLearningBase-v0.13.0)\n\n\n**Merged pull requests:**\n- Fix offline agent test (#1025) (@joelreymont)\n- Fix spell check CI errors (#1027) (@joelreymont)\n- GPU Code Migration Part 2.1 (#1029) (@jeremiahpslewis)\n- Bump RLZoo to v0.8 (#1031) (@jeremiahpslewis)\n- Fix RLZoo version (#1032) (@jeremiahpslewis)\n- Drop devmode, prepare RL.jl v0.11 for release (#1035) (@jeremiahpslewis)\n- Update docs script for new 'limited' RL.jl release (#1038) (@jeremiahpslewis)\n- Tabular Approximator fixes (pre v0.11 changes) (#1040) (@jeremiahpslewis)\n- Swap RLZoo for RLFarm in CI, drop RLExperiments (#1041) (@jeremiahpslewis)\n- Buildkite tweaks for monorepo (#1042) (@jeremiahpslewis)\n- Drop archived projects (#1043) (@jeremiahpslewis)\n- Simplify Experiment code after dropping RLExperiment (#1044) (@jeremiahpslewis)\n- Fix code coverage scope so it ignores test dir (#1045) (@jeremiahpslewis)\n- Fix reset and stop conditions (#1046) (@jeremiahpslewis)\n- Drop Functors and use Flux.@layer (#1048) (@jeremiahpslewis)\n- Fix naming consistency and add missing hook tests (#1049) (@jeremiahpslewis)\n- Add SARS tdlearning back to lib (#1050) (@jeremiahpslewis)\n- Update FluxModelApproximator references to FluxApproximator (#1051) (@jeremiahpslewis)\n- Epsilon Speedy Explorer (#1052) (@jeremiahpslewis)\n- Add TotalRewardPerEpisodeLastN hook (#1053) (@jeremiahpslewis)\n- Fix abstract_learner for multiplayer games (#1054) (@jeremiahpslewis)\n- Update versions (#1055) (@jeremiahpslewis)\n- Update Docs for v0.11 release (#1056) (@jeremiahpslewis)\n- Update Katex version, fix vulnerability (#1058) (@jeremiahpslewis)\n\n**Closed issues:**\n- RL Core tests fail sporadically (#1010)\n- Tutorial OpenSpiel KuhnOpenNSFP fails (#1024)\n- CI: Should spell check be dropped or fixed? (#1026)\n- Simple ReinforcementLearning example crashes (#1034)\n- Website: How do implement a new algorithm is outdated  (#1037)\n- Review TabularApproximator (#1039)","2024-03-26T17:17:00",{"id":172,"version":173,"summary_zh":174,"released_at":175},297380,"ReinforcementLearningExperiments-v0.4.0","## ReinforcementLearningExperiments ReinforcementLearningExperiments-v0.4.0\n\n\n\n**Merged pull requests:**\n- Fix deprecations (#10) (@femtocleaner[bot])\n- implement epsilon-greedy policy with parametric type (#12) (@jbrea)\n- improve docs (#13) (@jbrea)\n- refactor policies (#15) (@jbrea)\n- Add ReinforcementLearningBase as dependent (#16) (@jbrea)\n- fix examples (#18) (@jbrea)\n- refactor existing components (#26) (@findmyway)\n- Prioritized dqn (#29) (@findmyway)\n- add double dqn (#30) (@findmyway)\n- add rainbow (#31) (@findmyway)\n- use new api in ReinforcementLearningEnvironments.jl (#33) (@findmyway)\n- bugfix and api simplification (#34) (@findmyway)\n- Switch Tracker.jl to Zygote.jl (#37) (@findmyway)\n- Support both Knet and Flux(with Zygote) (#38) (@findmyway)\n- add docs (#39) (@findmyway)\n- export AbstractActionSelector and add more comments (#42) (@findmyway)\n- Refactor buffer (#45) (@findmyway)\n- fix example in doc && update examples (#46) (@findmyway)\n- fix a performance bug in rainbow (#47) (@findmyway)\n- update dependencies (#48) (@findmyway)\n- update dependencies and docs (#49) (@findmyway)\n- update benchmark for circular_array_buffer (#50) (@findmyway)\n- Install TagBot as a GitHub Action (#53) (@JuliaTagBot)\n- clean up code (#54) (@findmyway)\n- add compat (#55) (@findmyway)\n- CompatHelper: add new compat entry for \"Reexport\" at version \"0.2\" (#56) (@github-actions[bot])\n- add documentation stage in travis (#57) (@findmyway)\n- Add doc in travis (#58) (@findmyway)\n- Fix link in docs\u002Fsrc\u002Findex.md (#60) (@amanbh)\n- Update doc (#61) (@findmyway)\n- Update README.md & website link (#70) (@findmyway)\n- Update dependency (#78) (@findmyway)\n- MassInstallAction: Install the CompatHelper workflow on this repository (#99) (@findmyway)\n- CompatHelper: bump compat for \"Reexport\" to \"1.0\" (#172) (@github-actions[bot])\n- update dependency (#177) (@findmyway)\n- Add Dockerfile (#187) (@findmyway)\n- Update readme (#188) (@findmyway)\n- docs: add findmyway as a contributor (#189) (@allcontributors[bot])\n- docs: add drozzy as a contributor (#195) (@allcontributors[bot])\n- docs: add rcnlee as a contributor (#199) (@allcontributors[bot])\n- docs: add norci as a contributor (#200) (@allcontributors[bot])\n- docs: add xiruizhao as a contributor (#203) (@allcontributors[bot])\n- docs: add metab0t as a contributor (#204) (@allcontributors[bot])\n- docs: add albheim as a contributor (#207) (@allcontributors[bot])\n- docs: add michelangelo21 as a contributor (#214) (@allcontributors[bot])\n- docs: add pilgrimygy as a contributor (#216) (@allcontributors[bot])\n- docs: add Mobius1D as a contributor (#218) (@allcontributors[bot])\n- docs: add ilancoulon as a contributor (#224) (@allcontributors[bot])\n- docs: add pilgrimygy as a contributor (#230) (@allcontributors[bot])\n- docs: add JinraeKim as a contributor (#243) (@allcontributors[bot])\n- Prepare v0.9 (#252) (@findmyway)\n- docs: add luigiannelli as a contributor (#254) (@allcontributors[bot])\n- docs: add JBoerma as a contributor (#255) (@allcontributors[bot])\n- CompatHelper: bump compat for \"ReinforcementLearningEnvironments\" to \"0.5\" (#260) (@github-actions[bot])\n- Fix inconsitencies in wrappers (#263) (@albheim)\n- setup CI for each subpackages (#264) (@findmyway)\n- Fix atari experiments (#265) (@Mobius1D)\n- Add timeperstep hook to qrdqn to fix test error (#266) (@albheim)\n- Update Flux version (#267) (@findmyway)\n- Setup docs generation pipeline (#269) (@findmyway)\n- Misc doc related fixes (#270) (@findmyway)\n- Update README.md (#271) (@findmyway)\n- docs: add JinraeKim as a contributor (#272) (@allcontributors[bot])\n- Improve docs GitHub action (#273) (@findmyway)\n- Fix docs pipeline (#275) (@findmyway)\n- update readme (#276) (@findmyway)\n- CompatHelper: add new compat entry for \"UnicodePlots\" at version \"1.3\" for package ReinforcementLearningCore (#277) (@github-actions[bot])\n- CompatHelper: bump compat for \"Distributions\" to \"0.25\" for package ReinforcementLearningCore (#278) (@github-actions[bot])\n- CompatHelper: bump compat for \"Distributions\" to \"0.25\" for package ReinforcementLearningZoo (#279) (@github-actions[bot])\n- docs: add plu70n as a contributor (#282) (@allcontributors[bot])\n- Fix bug in CI (#283) (@findmyway)\n- Use Weave.jl to generate RLExperiments (#284) (@findmyway)\n- QRDQN experiment reproducibility fix (#294) (@ashwani-rathee)\n- Add Manifest.toml (#295) (@findmyway)\n- docs: add ashwani-rathee as a contributor (#296) (@allcontributors[bot])\n- Add basic doc structure (#300) (@findmyway)\n- Update guide (#302) (@findmyway)\n- Update experiments (#303) (@findmyway)\n- fix figs (#304) (@findmyway)\n- Fix some simple experiments (#308) (@findmyway)\n- add plotting for cartpole and mountaincar with Plots.jl (#309) (@jamblejoe)\n- Remove GR in RLEnvs (#310) (@findmyway)\n- docs: add jamblejoe as a contributor (#311) (@allcontributors[bot])\n- Add compat of Distributions@v0.24 in ReinforcementLearningExperiments (#312) (@findmyway)\n- Add example of SimplexSpace (#313) (@findmyway)\n- I","2024-03-07T11:12:06",{"id":177,"version":178,"summary_zh":179,"released_at":180},297381,"ReinforcementLearningZoo-v0.9.0","## ReinforcementLearningZoo ReinforcementLearningZoo-v0.9.0\n\n\n\n**Merged pull requests:**\n- Fix deprecations (#10) (@femtocleaner[bot])\n- implement epsilon-greedy policy with parametric type (#12) (@jbrea)\n- improve docs (#13) (@jbrea)\n- refactor policies (#15) (@jbrea)\n- Add ReinforcementLearningBase as dependent (#16) (@jbrea)\n- fix examples (#18) (@jbrea)\n- refactor existing components (#26) (@findmyway)\n- Prioritized dqn (#29) (@findmyway)\n- add double dqn (#30) (@findmyway)\n- add rainbow (#31) (@findmyway)\n- use new api in ReinforcementLearningEnvironments.jl (#33) (@findmyway)\n- bugfix and api simplification (#34) (@findmyway)\n- Switch Tracker.jl to Zygote.jl (#37) (@findmyway)\n- Support both Knet and Flux(with Zygote) (#38) (@findmyway)\n- add docs (#39) (@findmyway)\n- export AbstractActionSelector and add more comments (#42) (@findmyway)\n- Refactor buffer (#45) (@findmyway)\n- fix example in doc && update examples (#46) (@findmyway)\n- fix a performance bug in rainbow (#47) (@findmyway)\n- update dependencies (#48) (@findmyway)\n- update dependencies and docs (#49) (@findmyway)\n- update benchmark for circular_array_buffer (#50) (@findmyway)\n- Install TagBot as a GitHub Action (#53) (@JuliaTagBot)\n- clean up code (#54) (@findmyway)\n- add compat (#55) (@findmyway)\n- CompatHelper: add new compat entry for \"Reexport\" at version \"0.2\" (#56) (@github-actions[bot])\n- add documentation stage in travis (#57) (@findmyway)\n- Add doc in travis (#58) (@findmyway)\n- Fix link in docs\u002Fsrc\u002Findex.md (#60) (@amanbh)\n- Update doc (#61) (@findmyway)\n- Update README.md & website link (#70) (@findmyway)\n- Update dependency (#78) (@findmyway)\n- MassInstallAction: Install the CompatHelper workflow on this repository (#99) (@findmyway)\n- CompatHelper: bump compat for \"Reexport\" to \"1.0\" (#172) (@github-actions[bot])\n- update dependency (#177) (@findmyway)\n- Add Dockerfile (#187) (@findmyway)\n- Update readme (#188) (@findmyway)\n- docs: add findmyway as a contributor (#189) (@allcontributors[bot])\n- docs: add drozzy as a contributor (#195) (@allcontributors[bot])\n- docs: add rcnlee as a contributor (#199) (@allcontributors[bot])\n- docs: add norci as a contributor (#200) (@allcontributors[bot])\n- docs: add xiruizhao as a contributor (#203) (@allcontributors[bot])\n- docs: add metab0t as a contributor (#204) (@allcontributors[bot])\n- docs: add albheim as a contributor (#207) (@allcontributors[bot])\n- docs: add michelangelo21 as a contributor (#214) (@allcontributors[bot])\n- docs: add pilgrimygy as a contributor (#216) (@allcontributors[bot])\n- docs: add Mobius1D as a contributor (#218) (@allcontributors[bot])\n- docs: add ilancoulon as a contributor (#224) (@allcontributors[bot])\n- docs: add pilgrimygy as a contributor (#230) (@allcontributors[bot])\n- docs: add JinraeKim as a contributor (#243) (@allcontributors[bot])\n- Prepare v0.9 (#252) (@findmyway)\n- docs: add luigiannelli as a contributor (#254) (@allcontributors[bot])\n- docs: add JBoerma as a contributor (#255) (@allcontributors[bot])\n- CompatHelper: bump compat for \"ReinforcementLearningEnvironments\" to \"0.5\" (#260) (@github-actions[bot])\n- Fix inconsitencies in wrappers (#263) (@albheim)\n- setup CI for each subpackages (#264) (@findmyway)\n- Fix atari experiments (#265) (@Mobius1D)\n- Add timeperstep hook to qrdqn to fix test error (#266) (@albheim)\n- Update Flux version (#267) (@findmyway)\n- Setup docs generation pipeline (#269) (@findmyway)\n- Misc doc related fixes (#270) (@findmyway)\n- Update README.md (#271) (@findmyway)\n- docs: add JinraeKim as a contributor (#272) (@allcontributors[bot])\n- Improve docs GitHub action (#273) (@findmyway)\n- Fix docs pipeline (#275) (@findmyway)\n- update readme (#276) (@findmyway)\n- CompatHelper: add new compat entry for \"UnicodePlots\" at version \"1.3\" for package ReinforcementLearningCore (#277) (@github-actions[bot])\n- CompatHelper: bump compat for \"Distributions\" to \"0.25\" for package ReinforcementLearningCore (#278) (@github-actions[bot])\n- CompatHelper: bump compat for \"Distributions\" to \"0.25\" for package ReinforcementLearningZoo (#279) (@github-actions[bot])\n- docs: add plu70n as a contributor (#282) (@allcontributors[bot])\n- Fix bug in CI (#283) (@findmyway)\n- Use Weave.jl to generate RLExperiments (#284) (@findmyway)\n- QRDQN experiment reproducibility fix (#294) (@ashwani-rathee)\n- Add Manifest.toml (#295) (@findmyway)\n- docs: add ashwani-rathee as a contributor (#296) (@allcontributors[bot])\n- Add basic doc structure (#300) (@findmyway)\n- Update guide (#302) (@findmyway)\n- Update experiments (#303) (@findmyway)\n- fix figs (#304) (@findmyway)\n- Fix some simple experiments (#308) (@findmyway)\n- add plotting for cartpole and mountaincar with Plots.jl (#309) (@jamblejoe)\n- Remove GR in RLEnvs (#310) (@findmyway)\n- docs: add jamblejoe as a contributor (#311) (@allcontributors[bot])\n- Add compat of Distributions@v0.24 in ReinforcementLearningExperiments (#312) (@findmyway)\n- Add example of SimplexSpace (#313) (@findmyway)\n- Improve tutorial ","2024-03-07T09:36:55",{"id":182,"version":183,"summary_zh":184,"released_at":185},297382,"ReinforcementLearningEnvironments-v0.8.8","## ReinforcementLearningEnvironments ReinforcementLearningEnvironments-v0.8.8\n\n[Diff since ReinforcementLearningEnvironments-v0.8.7](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcompare\u002FReinforcementLearningEnvironments-v0.8.7...ReinforcementLearningEnvironments-v0.8.8)\n\n\n**Merged pull requests:**\n- Fix offline agent test (#1025) (@joelreymont)\n- Fix spell check CI errors (#1027) (@joelreymont)\n- GPU Code Migration Part 2.1 (#1029) (@jeremiahpslewis)\n\n**Closed issues:**\n- RL Core tests fail sporadically (#1010)\n- Tutorial OpenSpiel KuhnOpenNSFP fails (#1024)\n- CI: Should spell check be dropped or fixed? (#1026)","2024-03-06T22:09:23",{"id":187,"version":188,"summary_zh":189,"released_at":190},297383,"ReinforcementLearningCore-v0.14.0","## ReinforcementLearningCore ReinforcementLearningCore-v0.14.0\n\n[Diff since ReinforcementLearningCore-v0.13.1](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcompare\u002FReinforcementLearningCore-v0.13.1...ReinforcementLearningCore-v0.14.0)\n\n\n**Merged pull requests:**\n- Fix offline agent test (#1025) (@joelreymont)\n- Fix spell check CI errors (#1027) (@joelreymont)\n- GPU Code Migration Part 2.1 (#1029) (@jeremiahpslewis)\n\n**Closed issues:**\n- RL Core tests fail sporadically (#1010)\n- Tutorial OpenSpiel KuhnOpenNSFP fails (#1024)\n- CI: Should spell check be dropped or fixed? (#1026)","2024-03-06T22:09:11",{"id":192,"version":193,"summary_zh":194,"released_at":195},297384,"ReinforcementLearningEnvironments-v0.8.7","## ReinforcementLearningEnvironments ReinforcementLearningEnvironments-v0.8.7\n\n[Diff since ReinforcementLearningEnvironments-v0.8.6](https:\u002F\u002Fgithub.com\u002FJuliaReinforcementLearning\u002FReinforcementLearning.jl\u002Fcompare\u002FReinforcementLearningEnvironments-v0.8.6...ReinforcementLearningEnvironments-v0.8.7)","2024-03-04T08:50:23",{"id":197,"version":198,"summary_zh":199,"released_at":200},297385,"ReinforcementLearningEnvironments-v0.8.6","## ReinforcementLearningEnvironments ReinforcementLearningEnvironments-v0.8.6\n\n\n\n**Merged pull requests:**\n- Fix deprecations (#10) (@femtocleaner[bot])\n- implement epsilon-greedy policy with parametric type (#12) (@jbrea)\n- improve docs (#13) (@jbrea)\n- refactor policies (#15) (@jbrea)\n- Add ReinforcementLearningBase as dependent (#16) (@jbrea)\n- fix examples (#18) (@jbrea)\n- refactor existing components (#26) (@findmyway)\n- Prioritized dqn (#29) (@findmyway)\n- add double dqn (#30) (@findmyway)\n- add rainbow (#31) (@findmyway)\n- use new api in ReinforcementLearningEnvironments.jl (#33) (@findmyway)\n- bugfix and api simplification (#34) (@findmyway)\n- Switch Tracker.jl to Zygote.jl (#37) (@findmyway)\n- Support both Knet and Flux(with Zygote) (#38) (@findmyway)\n- add docs (#39) (@findmyway)\n- export AbstractActionSelector and add more comments (#42) (@findmyway)\n- Refactor buffer (#45) (@findmyway)\n- fix example in doc && update examples (#46) (@findmyway)\n- fix a performance bug in rainbow (#47) (@findmyway)\n- update dependencies (#48) (@findmyway)\n- update dependencies and docs (#49) (@findmyway)\n- update benchmark for circular_array_buffer (#50) (@findmyway)\n- Install TagBot as a GitHub Action (#53) (@JuliaTagBot)\n- clean up code (#54) (@findmyway)\n- add compat (#55) (@findmyway)\n- CompatHelper: add new compat entry for \"Reexport\" at version \"0.2\" (#56) (@github-actions[bot])\n- add documentation stage in travis (#57) (@findmyway)\n- Add doc in travis (#58) (@findmyway)\n- Fix link in docs\u002Fsrc\u002Findex.md (#60) (@amanbh)\n- Update doc (#61) (@findmyway)\n- Update README.md & website link (#70) (@findmyway)\n- Update dependency (#78) (@findmyway)\n- MassInstallAction: Install the CompatHelper workflow on this repository (#99) (@findmyway)\n- CompatHelper: bump compat for \"Reexport\" to \"1.0\" (#172) (@github-actions[bot])\n- update dependency (#177) (@findmyway)\n- Add Dockerfile (#187) (@findmyway)\n- Update readme (#188) (@findmyway)\n- docs: add findmyway as a contributor (#189) (@allcontributors[bot])\n- docs: add drozzy as a contributor (#195) (@allcontributors[bot])\n- docs: add rcnlee as a contributor (#199) (@allcontributors[bot])\n- docs: add norci as a contributor (#200) (@allcontributors[bot])\n- docs: add xiruizhao as a contributor (#203) (@allcontributors[bot])\n- docs: add metab0t as a contributor (#204) (@allcontributors[bot])\n- docs: add albheim as a contributor (#207) (@allcontributors[bot])\n- docs: add michelangelo21 as a contributor (#214) (@allcontributors[bot])\n- docs: add pilgrimygy as a contributor (#216) (@allcontributors[bot])\n- docs: add Mobius1D as a contributor (#218) (@allcontributors[bot])\n- docs: add ilancoulon as a contributor (#224) (@allcontributors[bot])\n- docs: add pilgrimygy as a contributor (#230) (@allcontributors[bot])\n- docs: add JinraeKim as a contributor (#243) (@allcontributors[bot])\n- Prepare v0.9 (#252) (@findmyway)\n- docs: add luigiannelli as a contributor (#254) (@allcontributors[bot])\n- docs: add JBoerma as a contributor (#255) (@allcontributors[bot])\n- CompatHelper: bump compat for \"ReinforcementLearningEnvironments\" to \"0.5\" (#260) (@github-actions[bot])\n- Fix inconsitencies in wrappers (#263) (@albheim)\n- setup CI for each subpackages (#264) (@findmyway)\n- Fix atari experiments (#265) (@Mobius1D)\n- Add timeperstep hook to qrdqn to fix test error (#266) (@albheim)\n- Update Flux version (#267) (@findmyway)\n- Setup docs generation pipeline (#269) (@findmyway)\n- Misc doc related fixes (#270) (@findmyway)\n- Update README.md (#271) (@findmyway)\n- docs: add JinraeKim as a contributor (#272) (@allcontributors[bot])\n- Improve docs GitHub action (#273) (@findmyway)\n- Fix docs pipeline (#275) (@findmyway)\n- update readme (#276) (@findmyway)\n- CompatHelper: add new compat entry for \"UnicodePlots\" at version \"1.3\" for package ReinforcementLearningCore (#277) (@github-actions[bot])\n- CompatHelper: bump compat for \"Distributions\" to \"0.25\" for package ReinforcementLearningCore (#278) (@github-actions[bot])\n- CompatHelper: bump compat for \"Distributions\" to \"0.25\" for package ReinforcementLearningZoo (#279) (@github-actions[bot])\n- docs: add plu70n as a contributor (#282) (@allcontributors[bot])\n- Fix bug in CI (#283) (@findmyway)\n- Use Weave.jl to generate RLExperiments (#284) (@findmyway)\n- QRDQN experiment reproducibility fix (#294) (@ashwani-rathee)\n- Add Manifest.toml (#295) (@findmyway)\n- docs: add ashwani-rathee as a contributor (#296) (@allcontributors[bot])\n- Add basic doc structure (#300) (@findmyway)\n- Update guide (#302) (@findmyway)\n- Update experiments (#303) (@findmyway)\n- fix figs (#304) (@findmyway)\n- Fix some simple experiments (#308) (@findmyway)\n- add plotting for cartpole and mountaincar with Plots.jl (#309) (@jamblejoe)\n- Remove GR in RLEnvs (#310) (@findmyway)\n- docs: add jamblejoe as a contributor (#311) (@allcontributors[bot])\n- Add compat of Distributions@v0.24 in ReinforcementLearningExperiments (#312) (@findmyway)\n- Add example of SimplexSpace (#313) (@findmyway)\n-","2024-03-03T21:43:36",{"id":202,"version":203,"summary_zh":204,"released_at":205},297386,"ReinforcementLearningCore-v0.13.1","## ReinforcementLearningCore ReinforcementLearningCore-v0.13.1\n\n\n\n**Merged pull requests:**\n- Fix deprecations (#10) (@femtocleaner[bot])\n- implement epsilon-greedy policy with parametric type (#12) (@jbrea)\n- improve docs (#13) (@jbrea)\n- refactor policies (#15) (@jbrea)\n- Add ReinforcementLearningBase as dependent (#16) (@jbrea)\n- fix examples (#18) (@jbrea)\n- refactor existing components (#26) (@findmyway)\n- Prioritized dqn (#29) (@findmyway)\n- add double dqn (#30) (@findmyway)\n- add rainbow (#31) (@findmyway)\n- use new api in ReinforcementLearningEnvironments.jl (#33) (@findmyway)\n- bugfix and api simplification (#34) (@findmyway)\n- Switch Tracker.jl to Zygote.jl (#37) (@findmyway)\n- Support both Knet and Flux(with Zygote) (#38) (@findmyway)\n- add docs (#39) (@findmyway)\n- export AbstractActionSelector and add more comments (#42) (@findmyway)\n- Refactor buffer (#45) (@findmyway)\n- fix example in doc && update examples (#46) (@findmyway)\n- fix a performance bug in rainbow (#47) (@findmyway)\n- update dependencies (#48) (@findmyway)\n- update dependencies and docs (#49) (@findmyway)\n- update benchmark for circular_array_buffer (#50) (@findmyway)\n- Install TagBot as a GitHub Action (#53) (@JuliaTagBot)\n- clean up code (#54) (@findmyway)\n- add compat (#55) (@findmyway)\n- CompatHelper: add new compat entry for \"Reexport\" at version \"0.2\" (#56) (@github-actions[bot])\n- add documentation stage in travis (#57) (@findmyway)\n- Add doc in travis (#58) (@findmyway)\n- Fix link in docs\u002Fsrc\u002Findex.md (#60) (@amanbh)\n- Update doc (#61) (@findmyway)\n- Update README.md & website link (#70) (@findmyway)\n- Update dependency (#78) (@findmyway)\n- MassInstallAction: Install the CompatHelper workflow on this repository (#99) (@findmyway)\n- CompatHelper: bump compat for \"Reexport\" to \"1.0\" (#172) (@github-actions[bot])\n- update dependency (#177) (@findmyway)\n- Add Dockerfile (#187) (@findmyway)\n- Update readme (#188) (@findmyway)\n- docs: add findmyway as a contributor (#189) (@allcontributors[bot])\n- docs: add drozzy as a contributor (#195) (@allcontributors[bot])\n- docs: add rcnlee as a contributor (#199) (@allcontributors[bot])\n- docs: add norci as a contributor (#200) (@allcontributors[bot])\n- docs: add xiruizhao as a contributor (#203) (@allcontributors[bot])\n- docs: add metab0t as a contributor (#204) (@allcontributors[bot])\n- docs: add albheim as a contributor (#207) (@allcontributors[bot])\n- docs: add michelangelo21 as a contributor (#214) (@allcontributors[bot])\n- docs: add pilgrimygy as a contributor (#216) (@allcontributors[bot])\n- docs: add Mobius1D as a contributor (#218) (@allcontributors[bot])\n- docs: add ilancoulon as a contributor (#224) (@allcontributors[bot])\n- docs: add pilgrimygy as a contributor (#230) (@allcontributors[bot])\n- docs: add JinraeKim as a contributor (#243) (@allcontributors[bot])\n- Prepare v0.9 (#252) (@findmyway)\n- docs: add luigiannelli as a contributor (#254) (@allcontributors[bot])\n- docs: add JBoerma as a contributor (#255) (@allcontributors[bot])\n- CompatHelper: bump compat for \"ReinforcementLearningEnvironments\" to \"0.5\" (#260) (@github-actions[bot])\n- Fix inconsitencies in wrappers (#263) (@albheim)\n- setup CI for each subpackages (#264) (@findmyway)\n- Fix atari experiments (#265) (@Mobius1D)\n- Add timeperstep hook to qrdqn to fix test error (#266) (@albheim)\n- Update Flux version (#267) (@findmyway)\n- Setup docs generation pipeline (#269) (@findmyway)\n- Misc doc related fixes (#270) (@findmyway)\n- Update README.md (#271) (@findmyway)\n- docs: add JinraeKim as a contributor (#272) (@allcontributors[bot])\n- Improve docs GitHub action (#273) (@findmyway)\n- Fix docs pipeline (#275) (@findmyway)\n- update readme (#276) (@findmyway)\n- CompatHelper: add new compat entry for \"UnicodePlots\" at version \"1.3\" for package ReinforcementLearningCore (#277) (@github-actions[bot])\n- CompatHelper: bump compat for \"Distributions\" to \"0.25\" for package ReinforcementLearningCore (#278) (@github-actions[bot])\n- CompatHelper: bump compat for \"Distributions\" to \"0.25\" for package ReinforcementLearningZoo (#279) (@github-actions[bot])\n- docs: add plu70n as a contributor (#282) (@allcontributors[bot])\n- Fix bug in CI (#283) (@findmyway)\n- Use Weave.jl to generate RLExperiments (#284) (@findmyway)\n- QRDQN experiment reproducibility fix (#294) (@ashwani-rathee)\n- Add Manifest.toml (#295) (@findmyway)\n- docs: add ashwani-rathee as a contributor (#296) (@allcontributors[bot])\n- Add basic doc structure (#300) (@findmyway)\n- Update guide (#302) (@findmyway)\n- Update experiments (#303) (@findmyway)\n- fix figs (#304) (@findmyway)\n- Fix some simple experiments (#308) (@findmyway)\n- add plotting for cartpole and mountaincar with Plots.jl (#309) (@jamblejoe)\n- Remove GR in RLEnvs (#310) (@findmyway)\n- docs: add jamblejoe as a contributor (#311) (@allcontributors[bot])\n- Add compat of Distributions@v0.24 in ReinforcementLearningExperiments (#312) (@findmyway)\n- Add example of SimplexSpace (#313) (@findmyway)\n- Improve tutori","2024-03-03T21:37:02",{"id":207,"version":208,"summary_zh":209,"released_at":210},297387,"ReinforcementLearningBase-v0.12.2","## ReinforcementLearningBase ReinforcementLearningBase-v0.12.2\n\n\n\n**Merged pull requests:**\n- Fix deprecations (#10) (@femtocleaner[bot])\n- implement epsilon-greedy policy with parametric type (#12) (@jbrea)\n- improve docs (#13) (@jbrea)\n- refactor policies (#15) (@jbrea)\n- Add ReinforcementLearningBase as dependent (#16) (@jbrea)\n- fix examples (#18) (@jbrea)\n- refactor existing components (#26) (@findmyway)\n- Prioritized dqn (#29) (@findmyway)\n- add double dqn (#30) (@findmyway)\n- add rainbow (#31) (@findmyway)\n- use new api in ReinforcementLearningEnvironments.jl (#33) (@findmyway)\n- bugfix and api simplification (#34) (@findmyway)\n- Switch Tracker.jl to Zygote.jl (#37) (@findmyway)\n- Support both Knet and Flux(with Zygote) (#38) (@findmyway)\n- add docs (#39) (@findmyway)\n- export AbstractActionSelector and add more comments (#42) (@findmyway)\n- Refactor buffer (#45) (@findmyway)\n- fix example in doc && update examples (#46) (@findmyway)\n- fix a performance bug in rainbow (#47) (@findmyway)\n- update dependencies (#48) (@findmyway)\n- update dependencies and docs (#49) (@findmyway)\n- update benchmark for circular_array_buffer (#50) (@findmyway)\n- Install TagBot as a GitHub Action (#53) (@JuliaTagBot)\n- clean up code (#54) (@findmyway)\n- add compat (#55) (@findmyway)\n- CompatHelper: add new compat entry for \"Reexport\" at version \"0.2\" (#56) (@github-actions[bot])\n- add documentation stage in travis (#57) (@findmyway)\n- Add doc in travis (#58) (@findmyway)\n- Fix link in docs\u002Fsrc\u002Findex.md (#60) (@amanbh)\n- Update doc (#61) (@findmyway)\n- Update README.md & website link (#70) (@findmyway)\n- Update dependency (#78) (@findmyway)\n- MassInstallAction: Install the CompatHelper workflow on this repository (#99) (@findmyway)\n- CompatHelper: bump compat for \"Reexport\" to \"1.0\" (#172) (@github-actions[bot])\n- update dependency (#177) (@findmyway)\n- Add Dockerfile (#187) (@findmyway)\n- Update readme (#188) (@findmyway)\n- docs: add findmyway as a contributor (#189) (@allcontributors[bot])\n- docs: add drozzy as a contributor (#195) (@allcontributors[bot])\n- docs: add rcnlee as a contributor (#199) (@allcontributors[bot])\n- docs: add norci as a contributor (#200) (@allcontributors[bot])\n- docs: add xiruizhao as a contributor (#203) (@allcontributors[bot])\n- docs: add metab0t as a contributor (#204) (@allcontributors[bot])\n- docs: add albheim as a contributor (#207) (@allcontributors[bot])\n- docs: add michelangelo21 as a contributor (#214) (@allcontributors[bot])\n- docs: add pilgrimygy as a contributor (#216) (@allcontributors[bot])\n- docs: add Mobius1D as a contributor (#218) (@allcontributors[bot])\n- docs: add ilancoulon as a contributor (#224) (@allcontributors[bot])\n- docs: add pilgrimygy as a contributor (#230) (@allcontributors[bot])\n- docs: add JinraeKim as a contributor (#243) (@allcontributors[bot])\n- Prepare v0.9 (#252) (@findmyway)\n- docs: add luigiannelli as a contributor (#254) (@allcontributors[bot])\n- docs: add JBoerma as a contributor (#255) (@allcontributors[bot])\n- CompatHelper: bump compat for \"ReinforcementLearningEnvironments\" to \"0.5\" (#260) (@github-actions[bot])\n- Fix inconsitencies in wrappers (#263) (@albheim)\n- setup CI for each subpackages (#264) (@findmyway)\n- Fix atari experiments (#265) (@Mobius1D)\n- Add timeperstep hook to qrdqn to fix test error (#266) (@albheim)\n- Update Flux version (#267) (@findmyway)\n- Setup docs generation pipeline (#269) (@findmyway)\n- Misc doc related fixes (#270) (@findmyway)\n- Update README.md (#271) (@findmyway)\n- docs: add JinraeKim as a contributor (#272) (@allcontributors[bot])\n- Improve docs GitHub action (#273) (@findmyway)\n- Fix docs pipeline (#275) (@findmyway)\n- update readme (#276) (@findmyway)\n- CompatHelper: add new compat entry for \"UnicodePlots\" at version \"1.3\" for package ReinforcementLearningCore (#277) (@github-actions[bot])\n- CompatHelper: bump compat for \"Distributions\" to \"0.25\" for package ReinforcementLearningCore (#278) (@github-actions[bot])\n- CompatHelper: bump compat for \"Distributions\" to \"0.25\" for package ReinforcementLearningZoo (#279) (@github-actions[bot])\n- docs: add plu70n as a contributor (#282) (@allcontributors[bot])\n- Fix bug in CI (#283) (@findmyway)\n- Use Weave.jl to generate RLExperiments (#284) (@findmyway)\n- QRDQN experiment reproducibility fix (#294) (@ashwani-rathee)\n- Add Manifest.toml (#295) (@findmyway)\n- docs: add ashwani-rathee as a contributor (#296) (@allcontributors[bot])\n- Add basic doc structure (#300) (@findmyway)\n- Update guide (#302) (@findmyway)\n- Update experiments (#303) (@findmyway)\n- fix figs (#304) (@findmyway)\n- Fix some simple experiments (#308) (@findmyway)\n- add plotting for cartpole and mountaincar with Plots.jl (#309) (@jamblejoe)\n- Remove GR in RLEnvs (#310) (@findmyway)\n- docs: add jamblejoe as a contributor (#311) (@allcontributors[bot])\n- Add compat of Distributions@v0.24 in ReinforcementLearningExperiments (#312) (@findmyway)\n- Add example of SimplexSpace (#313) (@findmyway)\n- Improve tutori","2024-03-03T20:15:58"]