CleanRL is a high-quality, single-file implementation library for deep reinforcement learning (Deep RL). It provides compact, research-friendly standalone implementations of many RL algorithms (PPO, DQN, C51, DDPG, TD3, SAC, PPG, etc.), benchmarks, TensorBoard logging, Weights & Biases integration, and cloud/run tooling. It emphasizes readability, reproducibility, and ease of understanding rather than being a modular importable framework.
