search

google-deepmind / dm_control

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Apache License 2.0
3.75k stars 665 forks source link

Mujoco Soccer simulation too slow #132

Open AlanLiaoyihang opened 4 years ago

AlanLiaoyihang commented 4 years ago

I am trying to train a 1v1 soccer games in the soccer environment. However, the training is really slow. Is there any method to speed up the simulation?

lich14 commented 4 years ago

Since you are running soccer. Do you have any idea on what each observation truly means.

Frank-Dz commented 2 years ago

Since you are running soccer. Do you have any idea on what each observation truly means.

I have the same question. Refer to my post: https://github.com/deepmind/dm_control/issues/271

Frank-Dz commented 2 years ago

I am trying to train a 1v1 soccer games in the soccer environment. However, the training is really slow. Is there any method to speed up the simulation?

I also met the same problem. The slowest part seems like the reset process after each episode.