PulseAugur
EN
LIVE 08:09:14

New FootsiesGym benchmark enables AI training in fighting games · 2 sources tracked

Researchers have introduced FootsiesGym, an open-source environment designed for training AI agents in two-player, zero-sum, imperfect-information games. Built upon the HiFight fighting game 'Footsies', this environment simplifies complex strategic interactions to facilitate efficient analysis and reproducible research. The system includes a vectorized simulator for high-throughput training and benchmarks several reinforcement learning algorithms, highlighting potential future research avenues. AI

IMPACT Provides a new, accessible platform for developing and testing reinforcement learning algorithms in complex strategic environments.

RANK_REASON The cluster contains an academic paper describing a new benchmark environment for AI research.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New FootsiesGym benchmark enables AI training in fighting games · 2 sources tracked

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Chase McDonald, Nathan Tsang, Wesley N. Kerr ·

    FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games

    arXiv:2607.06514v1 Announce Type: new 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 strat…

  2. arXiv cs.AI TIER_1 English(EN) · Wesley N. Kerr ·

    FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games

    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 …