Swain
在本 issue 中，我们会更新所有和课程第四讲相关的应用 demo 素材及训练日志（持续更新中） - minigrid 迷宫（奖励的稀疏性）[中文参考文档](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/minigrid_zh.html) - fourroom https://user-images.githubusercontent.com/33195032/220282567-b2ec7eb2-b8d3-47fb-9ac7-04bf353a8f7c.mp4 - doorkey https://user-images.githubusercontent.com/33195032/220282584-880c6e09-deda-4b76-9934-b3a0c201a7d5.mp4 - metadrive 自动驾驶 （奖励的多尺度变化）[中文参考文档](https://di-engine-docs.readthedocs.io/zh_CN/latest/13_envs/metadrive_zh.html) - fail cases https://user-images.githubusercontent.com/33195032/220282455-74133097-a29c-4bd8-b0ba-6b2840a24474.mp4 - success cases https://user-images.githubusercontent.com/49814804/218450981-4a72e55d-ec4d-4980-b52b-3bef6dbc72a0.mp4
It's really a very nice project, EDA design is a novel application of Deep Reinforcement Learning. I am the developer of [DI-engine](https://github.com/opendilab/DI-engine), looking for some interesting environments to apply advanced...
- [x] add basic task pipeline - [x] polish policy utils import - [ ] change the return value of `forward_collect/forward_eval` from `Dict` to `List` - [ ] change the...
Have you missed uploading some files? I checked the latest release tag but couldn't find them.