search

qgallouedec / panda-gym

Set of robotic environments based on PyBullet physics engine and gymnasium.
MIT License
506 stars 109 forks source link

Why the Panda Robot Env can only be trained by tqc in rl-baselines3-zoo? #13

Closed learningxiaobai closed 2 years ago

learningxiaobai commented 2 years ago

hello, I have another question is that Why the Panda Robot Env can only be trained by tqc, Are there any other RL algorithms in the rl-baselines3-zoo that can be used to train the Panda？ thanks.

learningxiaobai commented 2 years ago

hello, I have another question is that Why the Panda Robot Env can only be trained by tqc, Are there any other RL algorithms in the rl-baselines3-zoo that can be used to train the Panda？ thanks. by the way ，how long have you trained？ thanks.

qgallouedec commented 2 years ago

Since the environments of panda-gym are standard gym.Env, you can use every algorithm you want to train them : TQC or not, SB3 or not. (Of course, I cannot guaranty that the agent will actually learn something. This is the point of RL research. But the code will work.)