FootsiesGym: open two-player zero-sum imperfect-information benchmark for competitive agents

arXiv·medium signal

FootsiesGym is an open-source environment for learning in a non-trivial two-player, zero-sum, imperfect-information fighting game, giving agent researchers a tractable but meaningful testbed for self-play and adversarial reinforcement learning. It sits between toy matrix games and StarCraft-scale complexity. Relevant for anyone benchmarking competitive or multi-agent training loops.