Published October 8, 2024
| Version v1.0.0
Software
Open
Gymnasium: A Standard Interface for Reinforcement Learning Environments
Creators
- 1. University of Southampton & Farama Foundation
- 2. Farama Foundation
- 3. Independent Researcher
- 4. Mila, Université de Montréal
- 5. NeuralShift
- 6. Technical University of Crete (TUC)
- 7. EarthBrain
- 8. Brown University
- 9. University of Maryland
- 10. Coventry University
- 11. University of Bologna
Description
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.
Notes
Files
Farama-Foundation/Gymnasium-v1.0.0.zip
Files
(119.5 MB)
Name | Size | Download all |
---|---|---|
md5:63633d2a5c53a931631619d7672a7f0c
|
119.5 MB | Preview Download |
Additional details
Related works
- Is supplement to
- Software: https://github.com/Farama-Foundation/Gymnasium/tree/v1.0.0 (URL)