Home Page

Papers

Submissions

News

Editorial Board

Open Source Software

Proceedings (PMLR)

Transactions (TMLR)

Search

Statistics

Login

Frequently Asked Questions

Contact Us



RSS Feed

Stable-Baselines3: Reliable Reinforcement Learning Implementations

Antonin Raffin, Ashley Hill, Adam Gleave, Anssi Kanervisto, Maximilian Ernestus, Noah Dormann; 22(268):1−8, 2021.

Abstract

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 https://github.com/DLR-RM/stable-baselines3.

[abs][pdf][bib]        [code]
© JMLR 2021. (edit, beta)