I found a bug in file 'utils/util.py'. If we use discrete action space in 'runners\separated\mujoco_runner.py' and store it's transition in buffer, we will get a bug. Because the act_shape is a constant value.

cyanrain7 / TRPO-in-MARL

MIT License

186 stars 49 forks source link

Closed chillybird closed 2 years ago

chillybird commented 2 years ago

I test it in MPE

cyanrain7 commented 2 years ago

I test it in MPE

About the MPE runner, maybe you can refer the share version in MAPPO repo, it have some difference with mujoco runner.

chillybird commented 2 years ago

I understand ，thank you.