Reward bias in GAIL
Addressing reward bias in Adversarial Imitation Learning with unbiased reward functions in Tensorflow. Accepted at Deep RL workshop at NeurIPS 2020.
Official implementation of the paper Addressing reward bias in Adversarial Imitation Learning with neutral reward functions in Tensorflow.
This work was accepted at Deep RL workshop at NeurIPS 2020.
Github source code is here.