RNN related issues · thu-ml/tianshou#937

(12 评论) (0 反应) (0 负责人)Python (7,121 star) (1,072 fork)batch import

RNNbughelp wanted

描述

There is a bunch of reported RNN problems: #795 #513 #486 and some others. Generally, performance of agents with RNN on top never seemed to be good. This should be looked into, compared with other libraries, and fixed.

@Trinkle23897 @araffin @BFAnas If you have ideas where to start or whom to ping, feel free to write here. I guess it won't be an easy one...

Until this is solved, it might make sense to document that using RNNs is currently discouraged.

贡献者指南

技术栈: pythonpytorch
领域: machine learningai
议题类型: performance
难度: 5
预计时间: over 1 week
活动状态: stale
清晰度: mostly clear
前置要求: RNN in RLTianshou codebasePythonPyTorch
新手友好度: 20
研究方向: Investigate the performance issues with RNN based agents in Tianshou by examining the relevant code in the repository, likely in the policy or network modules. Compare with implementations in other RL libraries such as Stable Baselines3 to identify bottlenecks. The issue references #795, #513, and #486, which may contain specific reports and should be reviewed for context.