Open backpropper opened 4 years ago
https://github.com/junhyukoh/self-imitation-learning/blob/13eb8a79e9585f92761e0a4670bd76c2e0a7bf05/baselines/common/self_imitation.py#L262
I have the same confusion ... Can someone explain?
https://github.com/junhyukoh/self-imitation-learning/blob/13eb8a79e9585f92761e0a4670bd76c2e0a7bf05/baselines/common/self_imitation.py#L262