thu-ml/tianshou

How to support multi-agent reinforcement learning

Open

#121 创建于 2020年7月9日

在 GitHub 查看
 (34 评论) (1 反应) (1 负责人)Python (7,121 star) (1,072 fork)batch import
MARLdiscussiongood first issue

描述

  • I have marked all applicable categories:

    • exception-raising bug
    • RL algorithm bug
    • documentation request (i.e. "X is missing from the documentation.")
    • new feature request

  • I have visited the source website, and in particular read the known issues

  • I have searched through the issue tracker and issue categories for duplicates

  • I have mentioned version numbers, operating system and environment, where applicable:

    import tianshou, torch, sys
print(tianshou.__version__, torch.__version__, sys.version, sys.platform)

贡献者指南

技术栈
pythonpytorch
领域
machine learningai
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
4
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
over 1 week
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
unclear
前置要求
Understanding of multi agent RLFamiliarity with Tianshou codebasePyTorch proficiency
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
15
研究方向
Review the discussion in issue #121 for design considerations. Explore the Tianshou codebase, particularly the env and policy modules, to understand how single agent components are structured. Consider existing multi agent RL libraries like PettingZoo for environment abstractions. Assess feasibility of integrating multi agent support via wrappers or new policy classes.