MARS
MARS copied to clipboard
MARS is shortened for Multi-Agent Research Studio, a library for mulit-agent reinforcement learning research.
Results
2
MARS issues
Sort by
recently updated
recently updated
newest added
Hi, Recently, I was reproducing the nash-ppo algorithm. I would like to ask what is the purpose of common layer in nash-ppo algorithm? Thanks.
Hi, When I use nfsp to train my env, I encountered the following problem. `RuntimeError: Function 'SoftmaxBackward0' returnen nan values in its 0th output` By debugging, I found self.policy(state) outputed...