Pytorch A2c Ppo Acktr GailPyTorch 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).
macsimusA custom editor based on NeoVim and inspired from Vim and Emacs to maximise productivity.
atari-leaderboardA leaderboard of human and machine performance on the Arcade Learning Environment (ALE).