C++-based high-performance parallel environment execution engine (vector...
PyTorch implementation of Soft Actor-Critic (SAC)
RAD: Reinforcement Learning with Augmented Data
DrQ: Data regularized Q
PyTorch implementation of Soft Actor-Critic + Autoencoder(SAC+AE)
OpenAI Gym wrapper for the DeepMind Control Suite
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinfo...
Training code and evaluation benchmarks for the "Self-Supervised Policy ...
Convert DeepMind Control Suite to OpenAI gym environments.
Proto-RL: Reinforcement Learning with Prototypical Representations