Passerby

Goalkeeper bug in the built-in AI

3

When the AI learns to lob in multi agents, any strategy becomes meaningless😂. Maybe give the goalkeeper more bounce? you can watch some replay in this link https://www.bilibili.com/video/BV1n54y1V7bw  ...

[Suggestion] Zero Sum Rewards

1

Good job! Did you complete this project on your own? I believe that converting this into a self-play zero-sum game would yield excellent results. and remove derk.

Why is the result of this action the last column of the matrix?

1

What is the output of this action, quaternion or Euler angles? def mode(self) -> Tensor: return self._M[:, :, -1] [[https://github.com/stepjam/BPP/blob/main/stable_baselines_utils.py#L51](url)](https://github.com/stepjam/BPP/blob/3a2943dac8ef1a1dc85bf19abbc2b1ffde1b76a9/stable_baselines_utils.py#L50C1-L51C33)