{"id":"https://openalex.org/W7125921600","doi":"https://doi.org/10.1109/smc58881.2025.11342942","title":"Reinforcement Learning with Attention-based Multi-Scale Convolution Networks for Imperfect Information Games","display_name":"Reinforcement Learning with Attention-based Multi-Scale Convolution Networks for Imperfect Information Games","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125921600","doi":"https://doi.org/10.1109/smc58881.2025.11342942"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342942","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124113774","display_name":"Weilin Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weilin Yuan","raw_affiliation_strings":["Information Support Force Engineering University,Wuhan,China,430014"],"affiliations":[{"raw_affiliation_string":"Information Support Force Engineering University,Wuhan,China,430014","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090565823","display_name":"Zhenzhen Hu","orcid":"https://orcid.org/0000-0003-2807-8208"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenzhen Hu","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China,410072"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China,410072","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124123882","display_name":"Jiaxing Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2802541053","display_name":"Academy of Military Medical Sciences","ror":"https://ror.org/02bv3c993","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802541053"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxing Chen","raw_affiliation_strings":["Institute of Military Intelligence, Academy of Military Sciences,Beijing,China,100091"],"affiliations":[{"raw_affiliation_string":"Institute of Military Intelligence, Academy of Military Sciences,Beijing,China,100091","institution_ids":["https://openalex.org/I2802541053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061592286","display_name":"S. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaofei Chen","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China,410072"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China,410072","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100024299","display_name":"Weiwei Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Zhao","raw_affiliation_strings":["Information Support Force Engineering University,Wuhan,China,430014"],"affiliations":[{"raw_affiliation_string":"Information Support Force Engineering University,Wuhan,China,430014","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100771923","display_name":"Lina Lu","orcid":"https://orcid.org/0000-0003-1775-1831"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lina Lu","raw_affiliation_strings":["National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China,410072"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Intelligence Science and Technology,Changsha,China,410072","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5124113774"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87169093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7665","last_page":"7672"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.47119998931884766,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.47119998931884766,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.147599995136261,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.11010000109672546,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7342000007629395},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5957000255584717},{"id":"https://openalex.org/keywords/perfect-information","display_name":"Perfect information","score":0.5152999758720398},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4580000042915344},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4555000066757202},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.39160001277923584},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.3840999901294708},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.37720000743865967},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.3709000051021576}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7498999834060669},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7342000007629395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6697999835014343},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6015999913215637},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5957000255584717},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.5152999758720398},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4580000042915344},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4555000066757202},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.32710000872612},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.2996000051498413},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C92393732","wikidata":"https://www.wikidata.org/wiki/Q1790374","display_name":"Learning theory","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.25920000672340393},{"id":"https://openalex.org/C2779136372","wikidata":"https://www.wikidata.org/wiki/Q10283002","display_name":"Information flow","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342942","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2018887289","https://openalex.org/W2066327004","https://openalex.org/W2537003064","https://openalex.org/W2574978968","https://openalex.org/W2752782242","https://openalex.org/W2773381986","https://openalex.org/W2802011018","https://openalex.org/W3041349757","https://openalex.org/W3119316801","https://openalex.org/W3183328384","https://openalex.org/W4283815845"],"related_works":[],"abstract_inverted_index":{"Game":[0],"theory":[1,33],"plays":[2],"a":[3,19,80,106,188,198],"pivotal":[4],"role":[5],"in":[6,31,97,174],"addressing":[7],"Imperfect":[8],"Information":[9],"Games":[10],"(IIGs),":[11],"having":[12],"given":[13],"rise":[14],"to":[15,52,55,92,145,152,169],"the":[16,36,48,60,70,122,132,155,165,171,180,194,207,212],"development":[17],"of":[18,21,38,62,157,182,193,200,211],"suite":[20],"superhuman":[22],"agents.":[23],"However,":[24],"constructing":[25],"information":[26,50,115,124],"sets":[27],"and":[28,66,151,190,209],"game":[29,32,51],"trees":[30],"approaches":[34],"restricts":[35],"transferability":[37,210],"strategies.":[39],"Recently,":[40],"Reinforcement":[41],"Learning":[42],"(RL)":[43],"has":[44],"been":[45],"introduced":[46],"from":[47],"perfect":[49],"IIG,":[53],"owing":[54],"its":[56],"generalization":[57],"capabilities.":[58],"Yet,":[59],"challenges":[61],"efficient":[63],"feature":[64,102,114,128,149],"abstraction":[65],"stable":[67,81],"learning":[68,91,99],"within":[69,126],"RL":[71],"paradigm":[72],"persist.":[73],"To":[74],"address":[75],"these":[76],"challenges,":[77],"we":[78,104,163,186],"explore":[79],"actor-critic":[82],"training":[83],"framework":[84],"with":[85,139],"knowledge":[86,166],"distillation":[87,167],"based":[88],"on":[89,202],"supervised":[90],"enhance":[93],"proximal":[94,175],"policy":[95,176],"optimization":[96],"strategy":[98,161],"(MCA-PPO).":[100],"For":[101],"extraction,":[103],"engineer":[105],"multi-scale":[107,158],"convolutional":[108],"neural":[109],"network":[110,133],"that":[111],"amalgamates":[112],"local":[113],"across":[116],"various":[117],"receptive":[118],"field":[119],"sizes,":[120],"unearthing":[121],"latent":[123],"embedded":[125],"potential":[127],"sequences.":[129],"We":[130],"refine":[131],"architecture":[134],"further":[135],"by":[136],"integrating":[137],"it":[138,144],"an":[140],"attention":[141],"mechanism,":[142],"enabling":[143],"discern":[146],"relationships":[147],"between":[148],"channels":[150],"autonomously":[153],"identify":[154],"essence":[156],"features.":[159],"Regarding":[160],"learning,":[162],"employ":[164],"technique":[168],"mitigate":[170],"instability":[172],"inherent":[173],"optimization,":[177],"thereby":[178],"hastening":[179],"progression":[181],"strategic":[183],"learning.":[184],"Finally,":[185],"conducted":[187],"systematic":[189],"comprehensive":[191],"analysis":[192],"MCA-PPO":[195,213],"algorithm":[196],"through":[197],"series":[199],"experiments":[201],"Teax":[203],"Hold\u2019em":[204],"poker,":[205],"showing":[206],"efficacy":[208],"framework.":[214]},"counts_by_year":[],"updated_date":"2026-01-29T23:17:01.242718","created_date":"2026-01-29T00:00:00"}