Gymnasium: A Standard Interface for Reinforcement Learning Environments

作者：Mark Towers, Ariel Kwiatkowski, Jordan K. Terry, John U. Balis, G. Cola, T. Deleu, Manuel Goulão, Andreas Kallinteris, Markus Krimmel, KG Arjun, Rodrigo Perez-Vicente, Andrea Pierré, Sander Schulhoff, Jun Jet Tai, Hannah Tan, Omar G. Younis · 发表于：Neural Information Processing Systems · 年份：2025 · DOI：10.48550/arxiv.2407.17032 · 被引用次数：874 · 研究领域：Computer Science

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.