[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83456-en":3,"doc-seo-83456-105":30,"detail-sidebar-cat-0-en-105":91},{"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},83456,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253",8,"Research & Report","Play Like Champions: Counterfactual Feedback Generation in Latent Space","Recent reinforcement learning advances have enabled superhuman performance in competitive games, yet most work focuses on defeating human players rather than giving actionable feedback. For real-time strategy (RTS) games like StarCraft II, this paper proposes Latent Maps of Performance to generate counterfactual improvement paths in a learned representation space. A guided variational autoencoder is trained on 23,305 professional replays to traverse between losing and winning profiles. Four traversal strategies produce multi-step trajectories and feedback at multiple granularities, enabling player improvement grounded in expert behavior while moving toward winning configurations.","arXiv :2607 .00190v1 [ cs .LG] 30 Jun 2026  \nPLAY LIKE CHAMPIONS: COUNTERFACTUAL FEEDBACK GENERATION IN LATENT SPACE  \nA PREPRINT  \nAndrzej Białecki∗,1 , Adam Mastalerz∗,2 , Han Zhou∗,3  \n1Warsaw University of Technology  \n2 Silesian University of Technology  \n3University of British Columbia  \nABSTRACT  \nRecent advances in reinforcement learning have produced superhuman agents across a wide range of competitive games. As a byproduct, researchers have begun studying how these agents play, extracting behavioral representations, analyzing decision structure, and modeling the latent geometry of expert performance. However, this growing body of work has overwhelmingly focused on defeating human players rather than providing feedback, leaving a critical gap in creating model solutions to improve human players. Unlike chess and Go, where AI has become integral to player training, real-time strategy (RTS) games lack principled frameworks for translating expert knowledge into actionable feedback. We introduce Latent Maps of Performance, a framework for counterfactual path generation. We focus on StarCraft II data to model player improvement as an algorithmic recourse within a learned representation space. As inspiration for our work, we have looked at the championship model used in sports science. We trained a Guided Variational Autoencoder model on  \n23,305 professional tournament replays, with macro-economic gameplay structure conditioned on match outcome, enabling counterfactual traversal between losing and winning gameplay profiles. To fulfill our goal, we have devised and verified four traversal strategies on out-of-distribution (OOD) data randomly sampled from a dataset of amateur replays, namely linear interpolation, iterative optimal transport, density-regularized gradient ascent, and neural flow matching, each designed to generate multi-step improvement trajectories that remain grounded in observed expert behavior while moving a player’s profile toward winning configurations. Feedback is extracted at multiple granularities to support players at different stages of improvement. Finally, we conclude that there is a trade-off between the path-finding methods we employ and hope that future research will focus on developing model solutions for human improvement.  \nKeywords generative artificial intelligence · latent space traversal · optimal transport · variational autoencoder · esports  \n1 Introduction  \nMastering real-time strategy (RTS) games such as StarCraft II has long stood as a grand challenge for artificial intelligence, one only partially addressed by recent advances in reinforcement learning (RL) [1, 2] . The difficulty stems from the cognitive demands these games place on their players: precise control of units, careful management of economies, and continuous decision-making in adversarial settings where even momentary lapses can prove decisive. Success thus hinges on the interplay of multitasking, strategic foresight, and rapid reaction [3], making RTS an especially rich testbed for studying intelligent behavior. These high-frequency interactions make RTS games especially well-suited for large-scale behavioral study through open-source replay parsers and direct game-engine access [4, 5] . A growing body of work leverages data to surface game information for player decision support, both through digital interfaces and physical prototypes [6] . In StarCraft II, community tools such as sc2replaystats [7] and replayman [8] have emerged to support replay analysis, alongside real-time dashboards that contextualize gameplay for spectators and post-match review [9] . Strategic summaries and encounter-level analysis are highly valued by players across genres [10] . Game  \n* contact (in-order): [andrzej.bialecki94@gmail.com](andrzej.bialecki94@gmail.com), [adam.mastalerz@polsl.pl](adam.mastalerz@polsl.pl), [hzhou30@student.ubc.ca](hzhou30@student.ubc.ca)  \nstate retrieval by similarity to estimate win probabilities on demand is ","cbCailswHJDxQMty","https://ap.wps.com/l/cbCailswHJDxQMty","pdf",788325,3,1,19,"English","en",105,"# Introduction\n## Player-facing feedback gap\n## Motivation from sport science and digitized competition","[{\"question\":\"What problem does the paper address in RTS training?\",\"answer\":\"It addresses the lack of principled frameworks for turning expert AI knowledge into actionable feedback for human players in real-time strategy games.\"},{\"question\":\"How is counterfactual improvement generated in the proposed method?\",\"answer\":\"The method uses a learned latent representation space and Latent Maps of Performance to generate counterfactual paths that move a player profile from losing-like toward winning-like configurations.\"},{\"question\":\"Which traversal strategies are proposed to produce improvement trajectories?\",\"answer\":\"The paper devises and verifies four strategies on out-of-distribution amateur replay data: linear interpolation, iterative optimal transport, density-regularized gradient ascent, and neural flow matching.\"}]",1784188073,48,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"play-like-champions-counterfactual-feedback-generation-in-latent-space","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"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":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/play-like-champions-counterfactual-feedback-generation-in-latent-space/83456/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address in RTS training?","Question",{"text":75,"@type":76},"It addresses the lack of principled frameworks for turning expert AI knowledge into actionable feedback for human players in real-time strategy games.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is counterfactual improvement generated in the proposed method?",{"text":80,"@type":76},"The method uses a learned latent representation space and Latent Maps of Performance to generate counterfactual paths that move a player profile from losing-like toward winning-like configurations.",{"name":82,"@type":73,"acceptedAnswer":83},"Which traversal strategies are proposed to produce improvement trajectories?",{"text":84,"@type":76},"The paper devises and verifies four strategies on out-of-distribution amateur replay data: linear interpolation, iterative optimal transport, density-regularized gradient ascent, and neural flow matching.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"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":22,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]