mlsanityData to 14 Oct 2026

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

arXiv 2607.06514 ↗First posted 7 Jul 2026cs.AI cs.GTcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 19 references that are in the map. First posted on arXiv 7 Jul 2026.

Builds on

14 of 19 references.

References · 14

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 268
  3. 2020PettingZoo: Gym for Multi-Agent Reinforcement Learningcited by 220
  4. 2019OpenSpiel: A Framework for Reinforcement Learning in Gamescited by 186
  5. 2019Mastering Complex Control in MOBA Games with Deep Reinforcement Learningcited by 161
  6. 2022Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learningcited by 131
  7. 2022A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Gamescited by 66
  8. 2020Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Gamescited by 47
  9. 2022EvoJAX: Hardware-Accelerated Neuroevolutioncited by 29
  10. 2019Winning Isn't Everything: Enhancing Game Development with Intelligent Agentscited by 15
  11. 2025Reevaluating Policy Gradient Methods for Imperfect-Information Gamescited by 13
  12. 2022DareFightingICE Competition: A Fighting Game Sound Design and AI Competitioncited by 10
2 more
  1. 2022DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentationcited by 4
  2. 2026EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Gamescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning
  2. 2026Self-Play Reinforcement Learning under Imperfect Information in Big 2
  3. 2026NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games
  4. 2026A Gold-Standard Study of What Makes a Lightweight Game-Playing Agent Strong
  5. 2026Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games
  6. 2026Data-Augmented Game Starts for Accelerating Self-Play Exploration in Imperfect Information Games
  7. 2026BluffJAX: Adversarial Imperfect Information Games in JAX
  8. 2026GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games