How to judge the convergence
18627242758 opened this issue · comments
Jasonx commented
Hello!
Thanks so much for sharing the code!
I am new at inverse reinforcement learning. Now I am trying to apply AIRL and GAIL to a customized environment without knowing anything about the reward function. So are there any metrics that can be used to judge the convergence except for rewards?
Thanks ;).
Kai Arulkumaran commented
Yes, although this is difficult, Hyperparameter Selection for Imitation Learning proposes some.