Stable Baselines3 provides reliable 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.
RL Baselines Zoo provides scripts for Stable Baselines3 to train and evaluate agents, tune hyperparameters, record videos, store experiment setup and visualize results. We also include a collection of pre-trained reinforcement learning agents together with tuned hyperparameters for simple control tasks, PyBullet environments and Atari games, optimized using Optuna.
The code is available on Github: https://github.com/DLR-RM/stable-baselines3
Training Framework: https://github.com/DLR-RM/rl-baselines3-zoo