Abstract
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 FootsiesGym GitHub.
Blogger's Review: The launch of FootsiesGym provides an important experimental platform for studying imperfect information games, especially in the field of reinforcement learning. Its open-source and efficient code will attract more researchers' attention, pushing forward the development and application of related technologies.