lucidrains/ppo

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

RL implementations

Readable single-file PyTorch implementations of deep RL algorithms: DQN, PPO, SAC, TD3, DDPG and A2C, with Gymnasium and Atari support plus W&B tracking.

PyTorch Agent Net: reinforcement learning toolkit for pytorch

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

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

An elegant PyTorch deep reinforcement learning library.

Distributed Reinforcement Learning accelerated by Lightning Fabric

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code