FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games
The paper introduces FootsiesGym, an open-source environment for learning in a two-player, zero-sum, imperfect-information game, providing a vectorized simulator for efficient analysis.
The paper introduces an open-source environment, FootsiesGym, for learning in a non-trivial two-player game with a vectorized simulator.
Keywords
Before reading this…
Applications
- →Machine learning research
- →Game AI development
To understand this paper, make sure you know these concepts first:
- Understanding of reinforcement learningfind papers →
- Basic knowledge of game theoryfind papers →
Abstract
More Like ThisWe present FootsiesGym, an open-source environment for learning in a non-trivial two-player, zero-sum, imperfect-information game. Built on HiFight's minimalist 2D fighting game Footsies, it isolates the cyclic, non-transitive strategic interactions of fighting game neutral play while remaining simple enough for efficient analysis. We provide a vectorized simulator that enables high-throughput training on standard hardware, making the environment accessible and reproducible. We describe the design of the environment, benchmark several reinforcement learning algorithms, and discuss open research directions it enables. The code is available at https://github.com/como-research/FootsiesGym.