Stable-Baselines3: Reliable Reinforcement Learning Implementations


Stable-Baselines3 provides open-source implementations of deep reinforcement learning (RL) algorithms in Python. The implementations have been benchmarked against reference codebases, and automated unit tests cover 95% of the code. The algorithms follow a consistent interface and are accompanied by extensive documentation, making it simple to train and compare different RL algorithms. Our documentation, examples, and source-code are available at

Journal of Machine Learning Research
Adam Gleave
Adam Gleave
PhD Candidate in Artificial Intelligence

My research interests include value learning and robustness of deep RL.