Stable-Baselines3: Reliable Reinforcement Learning Implementations

Raffin, Antonin and Hill, Ashley and Gleave, Adam and Kanervisto, Anssi and Ernestus, Maximilian and Dormann, Noah (2021) Stable-Baselines3: Reliable Reinforcement Learning Implementations. Journal of Machine Learning Research. MIT Press. ISSN 1532-4435.

PDF - Postprint version (accepted manuscript)
232kB

Official URL: https://www.jmlr.org/papers/v22/20-1364.html

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.

Item URL in elib:

https://elib.dlr.de/146386/

Document Type:

Article

Title:

Stable-Baselines3: Reliable Reinforcement Learning Implementations

Authors:

Authors	Institution or Email of Authors	Author's ORCID iD	ORCID Put Code
Raffin, Antonin	UNSPECIFIED	https://orcid.org/0000-0001-6036-6950	UNSPECIFIED
Hill, Ashley	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED
Gleave, Adam	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED
Kanervisto, Anssi	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED
Ernestus, Maximilian	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED
Dormann, Noah	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED

Date:

2021

Journal or Publication Title:

Journal of Machine Learning Research

Refereed publication:

Yes

Open Access:

Yes

Gold Open Access:

In SCOPUS:

Yes

In ISI Web of Science:

Yes

Editors:

Editors	Email	Editor's ORCID iD	ORCID Put Code
Mueller, Andreas	UNSPECIFIED	UNSPECIFIED	UNSPECIFIED

Publisher:

MIT Press

ISSN:

1532-4435

Status:

Published

Keywords:

Reinforcement Learning, Baselines, Software, Open-Source, Python, PyTorch

HGF - Research field:

Aeronautics, Space and Transport

HGF - Program:

Space

HGF - Program Themes:

Robotics

DLR - Research area:

Raumfahrt

DLR - Program:

R RO - Robotics

DLR - Research theme (Project):

R - Autonomous learning robots [RO]

Location:

Oberpfaffenhofen

Institutes and Institutions:

Institute of Robotics and Mechatronics (since 2013) > Cognitive Robotics

Deposited By:

Raffin, Antonin

Deposited On:

30 Nov 2021 14:45

Last Modified:

02 Dec 2021 10:57

Repository Staff Only: item control page