[Unknown type: UNSPECIFIED]
Record type:
UNSPECIFIED
Abstract
Gymnasium is an open-source library providing an API for reinforcement learning environments. Its main contribution is a central abstraction for wide interoperability between benchmark environments and training algorithms. Gymnasium comes with various built-in environments and utilities to simplify researchers' work along with being supported by most training libraries. This paper outlines the main design decisions for Gymnasium, its key features, and the differences to alternative APIs.
Text
2407.17032v1
- Author's Original
Available under License Creative Commons Attribution.
Download (563kB)
More information
Published date: 24 July 2024
Additional Information:
1 figure
Keywords:
cs.LG, cs.DL
Identifiers
Local EPrints ID: 493069
URI: http://eprints.soton.ac.uk/id/eprint/493069
PURE UUID: 0bfabd73-5e3f-439b-abb8-bbe253fae27b
Catalogue record
Date deposited: 22 Aug 2024 16:56
Last modified: 23 Aug 2024 02:00
Export record
Altmetrics
Contributors
Author:
Mark Towers
Author:
Ariel Kwiatkowski
Author:
Jordan Terry
Author:
John U. Balis
Author:
Gianluca De Cola
Author:
Tristan Deleu
Author:
Manuel Goulão
Author:
Andreas Kallinteris
Author:
Markus Krimmel
Author:
K.G. Arjun
Author:
Rodrigo Perez-Vicente
Author:
Andrea Pierré
Author:
Sander Schulhoff
Author:
Jun Jet Tai
Author:
Hannah Tan
Author:
Omar G. Younis
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.