hongshaorou/Tianshou
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update experiment details of MuJoCo benchmark (#779)

Browse Source 
Update the downloading url of the training logs and saved checkpoints
for MuJoCo tasks.
This commit is contained in:
ChenDRAG 2022-11-27 02:18:22 +08:00 committed by GitHub
parent b9a6d8b5f0
commit 929508ba77
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/mujoco/README.md
View File

@ -321,7 +321,7 @@ For pretrained agents, detailed graphs (single agent, single game) and log detai
<a name="footnote1">[1]</a> Supported environments include HalfCheetah-v3, Hopper-v3, Swimmer-v3, Walker2d-v3, Ant-v3, Humanoid-v3, Reacher-v2, InvertedPendulum-v2 and InvertedDoublePendulum-v2. Pusher, Thrower, Striker and HumanoidStandup are not supported because they are not commonly seen in literatures.
<a name="footnote2">[2]</a> Pretrained agents, detailed graphs (single agent, single game) and log details can all be found at [https://cloud.tsinghua.edu.cn/d/f45fcfc5016043bc8fbc/](https://cloud.tsinghua.edu.cn/d/f45fcfc5016043bc8fbc/).
<a name="footnote2">[2]</a> Pretrained agents, detailed graphs (single agent, single game) and log details can all be found at [Google Drive](https://drive.google.com/drive/folders/1IycImzTmWcyEeD38viea5JHoboC4zmNP?usp=share_link).
<a name="footnote3">[3]</a> We used the latest version of all mujoco environments in gym (0.17.3 with mujoco==2.0.2.13), but it's not often the case with other benchmarks. Please check for details yourself in the original paper. (Different version's outcomes are usually similar, though)