CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms

By Shengyi Huang, Rousslan Fernand Julien Dossa, Chang Ye, Jeff Braga. Journal of machine learning research, 2022

510 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/c375c33093d2be25bafd894866ad959fab910c00

Citations in the corpus

• PettingZoo: Gym for Multi-Agent Reinforcement Learning (2020, unknown): “…PyMARL (ongoing) [Samvelyan et al., 2019], RLlib [Liang et al., 2018], Stable Baselines 2 [Hill et al., 2018] and Stable Baselines 3 [Raffin et al., 2019], similar libraries such as CleanRL [Huang et al., 2020] (through SuperSuit [Terry et al., 2020b]), and Tianshou (ongoing) [Weng et al., 2020].”
• Gymnasium: A Standard Interface for Reinforcement Learning Environments (2025, unknown): “CleanRL (Huang et al., 2022) is designed to provide clean, minimalistic implementations of RL algorithms.”