[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-oxwhirl--pymarl":3,"tool-oxwhirl--pymarl":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},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。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},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",140436,2,"2026-04-05T23:32:43",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},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。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":79,"owner_email":79,"owner_twitter":79,"owner_website":80,"owner_url":81,"languages":82,"stars":94,"forks":95,"last_commit_at":96,"license":97,"difficulty_score":10,"env_os":98,"env_gpu":99,"env_ram":99,"env_deps":100,"category_tags":106,"github_topics":79,"view_count":10,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":107,"updated_at":108,"faqs":109,"releases":139},1091,"oxwhirl\u002Fpymarl","pymarl","Python Multi-Agent Reinforcement Learning framework","pymarl是一个用于多智能体强化学习（MARL）的Python框架，支持多种经典算法如QMIX、COMA、VDN等，适用于训练多个智能体协同或竞争的决策系统。它基于PyTorch构建，集成StarCraft II（SC2）及其环境SMAC，可直接用于游戏场景中的多智能体训练与测试。框架提供了完整的配置系统，用户可通过简单命令启动实验，自动处理环境初始化、模型保存与结果记录。  \n\n该工具解决了多智能体协作与竞争场景下算法实现复杂、环境适配困难的问题，尤其针对需要高仿真环境的科研场景提供高效支持。适合具备Python编程基础的研究人员和开发者，尤其是从事多智能体强化学习、游戏AI或分布式系统研究的用户。其核心亮点在于对SC2生态的深度整合，以及对多种先进算法的标准化实现，降低了实验门槛。文档仍在完善中，但社区活跃度较高，可通过提交Issue获取帮助。","```diff\n- Please pay attention to the version of SC2 you are using for your experiments. \n- Performance is *not* always comparable between versions. \n- The results in SMAC (https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.04043) use SC2.4.6.2.69232 not SC2.4.10.\n```\n\n# Python MARL framework\n\nPyMARL is [WhiRL](http:\u002F\u002Fwhirl.cs.ox.ac.uk)'s framework for deep multi-agent reinforcement learning and includes implementations of the following algorithms:\n- [**QMIX**: QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F1803.11485)\n- [**COMA**: Counterfactual Multi-Agent Policy Gradients](https:\u002F\u002Farxiv.org\u002Fabs\u002F1705.08926)\n- [**VDN**: Value-Decomposition Networks For Cooperative Multi-Agent Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F1706.05296) \n- [**IQL**: Independent Q-Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F1511.08779)\n- [**QTRAN**: QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.05408)\n\nPyMARL is written in PyTorch and uses [SMAC](https:\u002F\u002Fgithub.com\u002Foxwhirl\u002Fsmac) as its environment.\n\n## Installation instructions\n\nBuild the Dockerfile using \n```shell\ncd docker\nbash build.sh\n```\n\nSet up StarCraft II and SMAC:\n```shell\nbash install_sc2.sh\n```\n\nThis will download SC2 into the 3rdparty folder and copy the maps necessary to run over.\n\nThe requirements.txt file can be used to install the necessary packages into a virtual environment (not recomended).\n\n## Run an experiment \n\n```shell\npython3 src\u002Fmain.py --config=qmix --env-config=sc2 with env_args.map_name=2s3z\n```\n\nThe config files act as defaults for an algorithm or environment. \n\nThey are all located in `src\u002Fconfig`.\n`--config` refers to the config files in `src\u002Fconfig\u002Falgs`\n`--env-config` refers to the config files in `src\u002Fconfig\u002Fenvs`\n\nTo run experiments using the Docker container:\n```shell\nbash run.sh $GPU python3 src\u002Fmain.py --config=qmix --env-config=sc2 with env_args.map_name=2s3z\n```\n\nAll results will be stored in the `Results` folder.\n\nThe previous config files used for the SMAC Beta have the suffix `_beta`.\n\n## Saving and loading learnt models\n\n### Saving models\n\nYou can save the learnt models to disk by setting `save_model = True`, which is set to `False` by default. The frequency of saving models can be adjusted using `save_model_interval` configuration. Models will be saved in the result directory, under the folder called *models*. The directory corresponding each run will contain models saved throughout the experiment, each within a folder corresponding to the number of timesteps passed since starting the learning process.\n\n### Loading models\n\nLearnt models can be loaded using the `checkpoint_path` parameter, after which the learning will proceed from the corresponding timestep. \n\n## Watching StarCraft II replays\n\n`save_replay` option allows saving replays of models which are loaded using `checkpoint_path`. Once the model is successfully loaded, `test_nepisode` number of episodes are run on the test mode and a .SC2Replay file is saved in the Replay directory of StarCraft II. Please make sure to use the episode runner if you wish to save a replay, i.e., `runner=episode`. The name of the saved replay file starts with the given `env_args.save_replay_prefix` (map_name if empty), followed by the current timestamp. \n\nThe saved replays can be watched by double-clicking on them or using the following command:\n\n```shell\npython -m pysc2.bin.play --norender --rgb_minimap_size 0 --replay NAME.SC2Replay\n```\n\n**Note:** Replays cannot be watched using the Linux version of StarCraft II. Please use either the Mac or Windows version of the StarCraft II client.\n\n## Documentation\u002FSupport\n\nDocumentation is a little sparse at the moment (but will improve!). Please raise an issue in this repo, or email [Tabish](mailto:tabish.rashid@cs.ox.ac.uk)\n\n## Citing PyMARL \n\nIf you use PyMARL in your research, please cite the [SMAC paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.04043).\n\n*M. Samvelyan, T. Rashid, C. Schroeder de Witt, G. Farquhar, N. Nardelli, T.G.J. Rudner, C.-M. Hung, P.H.S. Torr, J. Foerster, S. Whiteson. The StarCraft Multi-Agent Challenge, CoRR abs\u002F1902.04043, 2019.*\n\nIn BibTeX format:\n\n```tex\n@article{samvelyan19smac,\n  title = {{The} {StarCraft} {Multi}-{Agent} {Challenge}},\n  author = {Mikayel Samvelyan and Tabish Rashid and Christian Schroeder de Witt and Gregory Farquhar and Nantas Nardelli and Tim G. J. Rudner and Chia-Man Hung and Philiph H. S. Torr and Jakob Foerster and Shimon Whiteson},\n  journal = {CoRR},\n  volume = {abs\u002F1902.04043},\n  year = {2019},\n}\n```\n\n## License\n\nCode licensed under the Apache License v2.0\n","```diff\n- 请注意您在实验中使用的SC2（星际争霸2）版本。 \n- 不同版本之间的性能*不*总是可比。 \n- SMAC（https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.04043）中的结果使用SC2.4.6.2.69232而非SC2.4.10。\n```\n\n# Python多智能体强化学习框架\n\nPyMARL是[WhiRL](http:\u002F\u002Fwhirl.cs.ox.ac.uk)的深度多智能体强化学习框架，包含以下算法的实现：\n- [**QMIX**: QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F1803.11485)\n- [**COMA**: Counterfactual Multi-Agent Policy Gradients](https:\u002F\u002Farxiv.org\u002Fabs\u002F1705.08926)\n- [**VDN**: Value-Decomposition Networks For Cooperative Multi-Agent Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F1706.05296) \n- [**IQL**: Independent Q-Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F1511.08779)\n- [**QTRAN**: QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning](https:\u002F\u002Farxiv.org\u002Fabs\u002F1905.05408)\n\nPyMARL基于PyTorch编写，使用[SMAC](https:\u002F\u002Fgithub.com\u002Foxwhirl\u002Fsmac)作为环境。\n\n## 安装说明\n\n使用以下命令构建Dockerfile：\n```shell\ncd docker\nbash build.sh\n```\n\n设置StarCraft II和SMAC：\n```shell\nbash install_sc2.sh\n```\n\n这将下载SC2到3rdparty文件夹，并复制运行所需的地图。\n\nrequirements.txt文件可用于在虚拟环境中安装必要包（不推荐）。\n\n## 运行实验 \n\n```shell\npython3 src\u002Fmain.py --config=qmix --env-config=sc2 with env_args.map_name=2s3z\n```\n\n配置文件为算法或环境的默认设置。 \n\n它们全部位于`src\u002Fconfig`。\n`--config`指代`src\u002Fconfig\u002Falgs`中的配置文件\n`--env-config`指代`src\u002Fconfig\u002Fenvs`中的配置文件\n\n要使用Docker容器运行实验：\n```shell\nbash run.sh $GPU python3 src\u002Fmain.py --config=qmix --env-config=sc2 with env_args.map_name=2s3z\n```\n\n所有结果将存储在`Results`文件夹中。\n\nSMAC Beta之前的配置文件带有后缀 `_beta`。\n\n## 保存和加载学习模型\n\n### 保存模型\n\n通过设置`save_model = True`可以将学习模型保存到磁盘（默认为False）。可通过`save_model_interval`配置调整保存频率。模型将保存在结果目录下的*models*文件夹中。每个运行对应的目录将包含实验过程中保存的模型，每个模型存储在以学习过程开始后经过的步数命名的子文件夹中。\n\n### 加载模型\n\n通过`checkpoint_path`参数加载学习模型后，学习将从对应的时间步继续进行。\n\n## 观看StarCraft II回放\n\n`save_replay`选项允许保存通过`checkpoint_path`加载的模型的回放。一旦模型成功加载，`test_nepisode`数量的回合将在测试模式下运行，并在StarCraft II的Replay目录中保存一个.SC2Replay文件。请确保使用episode运行器（即`runner=episode`）如果希望保存回放，回放文件名以给定的`env_args.save_replay_prefix`（若为空则为map_name）开头，后接当前时间戳。\n\n保存的回放可通过双击文件或使用以下命令观看：\n\n```shell\npython -m pysc2.bin.play --norender --rgb_minimap_size 0 --replay NAME.SC2Replay\n```\n\n**注意：** 无法使用Linux版StarCraft II观看回放。请使用Mac或Windows版StarCraft II客户端。\n\n## 文档\u002F支持\n\n目前文档内容较少（但会逐步完善！）。请在此仓库中提交问题，或发送邮件至[Tabish](mailto:tabish.rashid@cs.ox.ac.uk)\n\n## 引用PyMARL \n\n如果在研究中使用PyMARL，请引用[SMAC论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F1902.04043)。\n\n*M. Samvelyan, T. Rashid, C. Schroeder de Witt, G. Farquhar, N. Nardelli, T.G.J. Rudner, C.-M. Hung, P.H.S. Torr, J. Foerster, S. Whiteson. The StarCraft Multi-Agent Challenge, CoRR abs\u002F1902.04043, 2019.*\n\nBibTeX格式：\n\n```tex\n@article{samvelyan19smac,\n  title = {{The} {StarCraft} {Multi}-{Agent} {Challenge}},\n  author = {Mikayel Samvelyan and Tabish Rashid and Christian Schroeder de Witt and Gregory Farquhar and Nantas Nardelli and Tim G. J. Rudner and Chia-Man Hung and Philiph H. S. Torr and Jakob Foerster and Shimon Whiteson},\n  journal = {CoRR},\n  volume = {abs\u002F1902.04043},\n  year = {2019},\n}\n```\n\n## 许可证\n\n代码遵循Apache License v2.0许可","# PyMARL 快速上手指南\n\n## 环境准备\n- **系统要求**：Python 3.6+，PyTorch 1.8+\n- **前置依赖**：\n  - StarCraft II 游戏环境（需安装SC2.4.6.2.69232版本）\n  - SMAC 环境（需通过`install_sc2.sh`脚本安装）\n  - Docker（用于容器化部署）\n\n## 安装步骤\n1. 构建Docker镜像\n```shell\ncd docker\nbash build.sh\n```\n\n2. 安装StarCraft II和SMAC\n```shell\nbash install_sc2.sh\n```\n\n3. 安装依赖（建议使用国内镜像源）\n```shell\npip install -r requirements.txt -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n```\n\n## 基本使用\n运行QMIX算法在SC2环境中的示例：\n```shell\npython3 src\u002Fmain.py --config=qmix --env-config=sc2 with env_args.map_name=2s3z\n```\n\n使用Docker容器运行：\n```shell\nbash run.sh $GPU python3 src\u002Fmain.py --config=qmix --env-config=sc2 with env_args.map_name=2s3z\n```\n\n所有实验结果会保存在`Results`目录下。","游戏AI研发团队在训练StarCraft II多智能体对抗策略时，面临复杂环境建模和算法实现难题。  \n\n### 没有 pymarl 时  \n- 多智能体协作策略需手动实现算法逻辑，开发效率低  \n- 环境接口复杂，需自行处理SC2版本兼容性问题  \n- 训练过程难以监控，无法实时调整参数  \n- 不同算法切换需重复编写大量基础代码  \n- 结果复现困难，版本控制缺乏统一标准  \n\n### 使用 pymarl 后  \n- 通过内置的QMIX\u002FCOMA等算法模板，快速搭建协作策略  \n- 自动处理SC2环境版本差异，确保实验一致性  \n- 提供可视化界面实时追踪训练进度和策略表现  \n- 一键切换算法配置，减少重复代码编写  \n- 标准化保存模型和 replay 文件，实现实验可复现  \n\n核心价值在于为多智能体强化学习提供标准化开发框架，显著降低复杂环境下的算法实现门槛。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Foxwhirl_pymarl_6e413bbc.png","oxwhirl","whirl","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Foxwhirl_2d6fbc71.png","Whiteson Research Lab",null,"https:\u002F\u002Fwhirl.cs.ox.ac.uk\u002F","https:\u002F\u002Fgithub.com\u002Foxwhirl",[83,87,91],{"name":84,"color":85,"percentage":86},"Python","#3572A5",95.8,{"name":88,"color":89,"percentage":90},"Shell","#89e051",2.2,{"name":92,"color":93,"percentage":23},"Dockerfile","#384d54",2176,411,"2026-04-02T11:31:43","Apache-2.0","macOS, Windows","未说明",{"notes":101,"python":99,"dependencies":102},"建议使用 conda 管理环境，首次运行需下载约 5GB 模型文件",[103,104,105],"torch","smac","pysc2",[13,15],"2026-03-27T02:49:30.150509","2026-04-06T08:40:52.022350",[110,115,120,125,130,135],{"id":111,"question_zh":112,"answer_zh":113,"source_url":114},4898,"如何解决Docker构建时的兼容性问题？","在安装SMAC时，若出现jsonpickle版本冲突，可修改q_learner.py文件，将第73-74行替换为：\n`mac_out_detach = mac_out.clone().detach()`\n`mac_out_detach[avail_actions == 0] = -9999999`\n`cur_max_actions = mac_out_detach[:, 1:].max(dim=3, keepdim=True)[1]`","https:\u002F\u002Fgithub.com\u002Foxwhirl\u002Fpymarl\u002Fissues\u002F27",{"id":116,"question_zh":117,"answer_zh":118,"source_url":119},4899,"Windows系统下如何解决sacred模块的异常问题？","修改sacred模块的stdout_capturing.py文件，将第136行的异常捕获语句改为：\n`except (FileNotFoundError, OSError, AttributeError):`","https:\u002F\u002Fgithub.com\u002Foxwhirl\u002Fpymarl\u002Fissues\u002F8",{"id":121,"question_zh":122,"answer_zh":123,"source_url":124},4900,"如何解决StarCraft II回放无法播放的问题？","使用以下命令播放回放文件：\n`python3 -m pysc2.bin.play --norender --rgb_minimap_size 0 --replay NAME.SC2Replay`","https:\u002F\u002Fgithub.com\u002Foxwhirl\u002Fpymarl\u002Fissues\u002F5",{"id":126,"question_zh":127,"answer_zh":128,"source_url":129},4901,"如何解决多智能体环境中动作冲突的错误？","该错误通常由智能体动作不匹配导致，可尝试以下方法：\n1. 检查环境配置文件中的动作空间定义\n2. 确保所有智能体的动作范围一致\n3. 在训练时增加动作有效性校验逻辑","https:\u002F\u002Fgithub.com\u002Foxwhirl\u002Fpymarl\u002Fissues\u002F13",{"id":131,"question_zh":132,"answer_zh":133,"source_url":134},4902,"如何正确使用COMA算法中的基线模型？","COMA算法中的基线模型（如Central-V、IAC-V）需要：\n1. 正确配置环境参数（如map_name）\n2. 使用官方提供的Critic函数实现模板\n3. 确保输入格式符合论文要求（如状态表示方式）","https:\u002F\u002Fgithub.com\u002Foxwhirl\u002Fpymarl\u002Fissues\u002F18",{"id":136,"question_zh":137,"answer_zh":138,"source_url":134},4903,"QMIX与COMA算法的实验对比结果如何？","根据SMAC论文实验，QMIX在SMAC环境中通常优于COMA，但COMA在部分场景下表现更优。建议：\n1. 使用官方提供的对比实验配置\n2. 确保环境版本与论文一致\n3. 检查超参数设置是否匹配",[]]