search

conglu1997 / v-d4rl

Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations
MIT License
94 stars 9 forks source link

Generating Humanoid Dataset #11

Closed gunnxx closed 9 months ago

gunnxx commented 9 months ago

Hi, this might be not the place but I am just wondering what hyperparameters did you use to train the SAC agent (data collection policy) for Humanoid Walk? The default hyperparameters successfully achieve expert level performance for 1M steps for Walker Walk and Cheetah Run. I use this codebase as mentioned in the README.

conglu1997 commented 9 months ago

I believe you'll need 10M steps for expert on that environment.

gunnxx commented 9 months ago

Okay noted. Thanks a lot for the quick reply, appreciate it!