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).
MIT License
3.53k
stars
832
forks
source link
Update: Support the latest Atari environments. #297
Some updates for supporting the latest Atari environment:
stable-baselines3==1.5.0 gym==0.21.0 ale-py==0.7.4
The update has been tested!