search

erwincoumans / motion_imitation

Code accompanying the paper "Learning Agile Robotic Locomotion Skills by Imitating Animals"
Apache License 2.0
1.17k stars 292 forks source link

Adapting this implementation of PPO for DeepMimic #39

Closed tfederico closed 3 years ago

tfederico commented 4 years ago

Hello,

I wanted to ask if you think it would be feasible to adapt this implementation of PPO using stable_baselines to DeepMimic. If so, which are the main differences in the learning algorithm?

By reading both papers, it didn't look like there were major differences in the PPO implementation, apart from the reward functions.

Is there any specific reason why you decided to use PPO1 instead of PPO2?

erwincoumans commented 3 years ago

This implementation is using stable baselines.