PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
Hello, I am a little confused about compute_grad_pen function in gail.py, Cound someone can tell me? why we need this in this file? and what relation between this with GAIL?
Hello, I am a little confused about compute_grad_pen function in gail.py, Cound someone can tell me? why we need this in this file? and what relation between this with GAIL?