FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games
Provides a simplified yet non-trivial benchmark for researchers studying strategic interactions in imperfect-information games, enabling efficient analysis and high-throughput training.
The paper introduces FootsiesGym, an open-source environment for studying two-player zero-sum imperfect-information games based on a minimalist fighting game, and benchmarks several RL algorithms, demonstrating its utility for efficient analysis and reproducible research.
We 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.