stable-baselines3 and stable-baselines3-contrib
The contrib package extends the main library with experimental RL algorithms and features, making them complements designed to be used together rather than alternatives.
About stable-baselines3
DLR-RM/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
This is a tool for machine learning researchers and practitioners working with Reinforcement Learning (RL). It provides reliable, tested implementations of various RL algorithms. You input a defined environment and an RL algorithm, and it outputs a trained agent that can learn to make decisions within that environment.
About stable-baselines3-contrib
Stable-Baselines-Team/stable-baselines3-contrib
Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
This project provides experimental reinforcement learning (RL) algorithms and tools for tasks like training agents to play games, control robots, or optimize complex systems. It takes in environment observations and outputs optimized decision-making policies. This is for machine learning researchers and practitioners who want to explore cutting-edge RL techniques.
Scores updated daily from GitHub, PyPI, and npm data. How scores work