High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Code for the paper "On the Importance of Feature Decorrelation for Unsupervised Representation Learning for RL" (ICML 2023)

Plug-and-play hydra sweepers for the EA-based multifidelity method DEHB and several population-based training variations, all proven to efficiently tune RL hyperparameters.

Example models using DeepSpeed

Actor Prioritized Experience Replay

SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.