[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84123-en":3,"doc-seo-84123-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},84123,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games","FootsiesGym提供一个开源学习环境，用于研究双人零和、不完全信息且结构上具有非平凡性的对抗博弈。该环境基于HiFight的极简2D格斗游戏Footsies，聚焦中立对局阶段中循环且非传递的策略相互作用，并在保持建模简洁的同时方便高效分析。文中给出向量化模拟器以支持在标准硬件上的高吞吐训练，描述环境设计、对多种强化学习算法进行基准评测，并讨论由此启用的开放研究方向。代码已公开。","arXiv :2607 .065 14v 1 [ cs .AI ] 7 Jul 2026  \nFootsiesGym: A Fighting Game Benchmark for TwoPlayer Zero-Sum Imperfect-Information Games  \nChase McDonald 1 , Nathan Tsang2 , Wesley N. Kerr2  \n[chase@comoresearch.org](chase@comoresearch.org) , {ntsang, [wkerr}@riotgames.com](wkerr}@riotgames.com)  \n1 Como Research  \n2 Riot Games  \nAbstract  \nWe present FootsiesGym, an open-source environment for learning in a non-trivial twoplayer, 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/](https://github.com/)[ ](https://github.com/)como-research/FootsiesGym.  \n1 Introduction  \nProgress in multi-agent and game-theoretic reinforcement learning depends on benchmarks that capture the right structure at a tractable cost. Existing environments tend toward two extremes. On one side are clean game-theoretic benchmarks such as matrix games and poker variants, which expose cyclic, mixed-strategy structure but typically have short horizons, simple dynamics, and limited exploration requirements. On the other are large, real-time environments (e.g., StarCraft II and Dota 2), which are deeply complex with long time horizons, but require extensive resources for training.  \nFighting games can occupy a productive middle ground: they are real-time and spatial, yet keep the strategic structure front and center. They rely on fundamentally non-transitive dynamics based on the interaction between two opposing players. The basic strategy in fighting games is often described as a game of rock-paper-scissors, as players must learn mixed strategies over the primitives of movement and the different kinds of attacks that counter each other and form strategy cycles. Because no single option dominates, a player who commits to a pure strategy can be easily exploited.  \nIn this work, we provide a benchmark environment to study these interactions in Footsies (HiFight, 2018), an open-source 2D fighter by HiFight, shown in Figure 1. Footsies is built around the neutral game: the phase in which neither player has a clear advantage, and both players maneuver, adjust their spacing and timing, and attempt to create an opening to attack. This is precisely where the cyclic, mixed-strategy structure described above emerges.  \n2 Related Work  \nBenchmark Environments. Multi-agent and game-theoretic reinforcement learning research spans a wide range of environment complexity. On one end, there are the small-scale environments that permit exact exploitability calculations (Lanctot et al., 2019 ; Rudolph et al., 2025), such  \nFigure 1: A screenshot of the Footsies game, from HiFight (2018) . Two characters fight one another using a combination of movement, quick attacks, and special attacks. A player wins when they K.O. the other.  \nas Kuhn Poker, Goofspiel, Leduc Poker, Phantom Tic-Tac-Toe, and Dark Hex. While these environments are valuable for exact exploitability calculations and equilibrium analysis, they capture little of the complexity of richer games. On the other end, real-time strategy and MOBA environments such as StarCraft II (Vinyals et al., 2019) and Honor of Kings (Ye et al., 2020) have rich, long-horizon dynamics but demand substantial compute and time to train. Between these extremes, environments such as Slime Volleyball (Tang et al., 2022) and simplified Stratego variants (e.g., McAleer et al., 2020) offer intermediate complexity at moderate cost. FootsiesGym likewise occupies this middle ground: it is real-time, spatial, imperfect-information,","cbCaihO2TWxhvHvO","https://ap.wps.com/l/cbCaihO2TWxhvHvO","pdf",1926018,5,1,14,"English","en",105,"# Abstract\n# Introduction\n# Related Work\n# FootsiesGym Environment","[{\"question\":\"FootsiesGym的核心用途是什么？\",\"answer\":\"FootsiesGym是一个开源环境，用于在双人零和、不完全信息的对抗博弈中开展学习与研究，重点刻画格斗游戏中中立阶段的循环、非传递战略相互作用。\"},{\"question\":\"FootsiesGym如何在复杂度与可分析性之间取得平衡？\",\"answer\":\"它基于极简的2D格斗游戏Footsies，通过刻意聚焦中立对局阶段来隔离循环混合策略结构，同时避免进入更偏执行性的连招阶段，从而降低分析负担并保持可训练性。\"},{\"question\":\"FootsiesGym提供了哪些关键实现以支持高效训练？\",\"answer\":\"文中给出向量化模拟器，用于在标准硬件上实现高吞吐训练；同时强调环境设计、基准评测若干强化学习算法，并保持开源与可复现性。\"}]",1784193096,35,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"footsiesgym-a-fighting-game-benchmark-for-two-player-zero-sum-imperfect-information-games","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/footsiesgym-a-fighting-game-benchmark-for-two-player-zero-sum-imperfect-information-games/84123/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-28","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"FootsiesGym的核心用途是什么？","Question",{"text":76,"@type":77},"FootsiesGym是一个开源环境，用于在双人零和、不完全信息的对抗博弈中开展学习与研究，重点刻画格斗游戏中中立阶段的循环、非传递战略相互作用。","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"FootsiesGym如何在复杂度与可分析性之间取得平衡？",{"text":81,"@type":77},"它基于极简的2D格斗游戏Footsies，通过刻意聚焦中立对局阶段来隔离循环混合策略结构，同时避免进入更偏执行性的连招阶段，从而降低分析负担并保持可训练性。",{"name":83,"@type":74,"acceptedAnswer":84},"FootsiesGym提供了哪些关键实现以支持高效训练？",{"text":85,"@type":77},"文中给出向量化模拟器，用于在标准硬件上实现高吞吐训练；同时强调环境设计、基准评测若干强化学习算法，并保持开源与可复现性。","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":20,"slug":138},19,"General","general"]