{"id":"https://openalex.org/W4312850441","doi":"https://doi.org/10.1109/tg.2022.3226526","title":"WagerWin: An Efficient Reinforcement Learning Framework for Gambling Games","display_name":"WagerWin: An Efficient Reinforcement Learning Framework for Gambling Games","publication_year":2022,"publication_date":"2022-12-05","ids":{"openalex":"https://openalex.org/W4312850441","doi":"https://doi.org/10.1109/tg.2022.3226526"},"language":"en","primary_location":{"id":"doi:10.1109/tg.2022.3226526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2022.3226526","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-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/A5020363814","display_name":"Haoli Wang","orcid":"https://orcid.org/0000-0001-5405-0642"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoli Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5405-0642","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102755158","display_name":"Hejun Wu","orcid":"https://orcid.org/0000-0001-9758-5698"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hejun Wu","raw_affiliation_strings":["Department of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9758-5698","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023017682","display_name":"Guoming Lai","orcid":"https://orcid.org/0000-0002-3675-4977"},"institutions":[{"id":"https://openalex.org/I93477617","display_name":"Huizhou University","ror":"https://ror.org/03q3s7962","country_code":"CN","type":"education","lineage":["https://openalex.org/I93477617"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoming Lai","raw_affiliation_strings":["School of Computer Science and Engineering, Huizhou University, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-3675-4977","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Huizhou University, Guangdong, China","institution_ids":["https://openalex.org/I93477617"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3484,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66081943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"15","issue":"3","first_page":"483","last_page":"491"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9980000257492065,"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/T11674","display_name":"Sports Analytics and Performance","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8387695550918579},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6736040115356445},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5801424980163574},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5312784910202026},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5300101041793823},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5289521217346191},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.512923002243042},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.49439263343811035},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4365314841270447},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.42539846897125244},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.4235055446624756},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3607335686683655},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2501712441444397},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20736154913902283},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17572584748268127},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14450570940971375},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.0763055682182312}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8387695550918579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6736040115356445},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5801424980163574},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5312784910202026},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5300101041793823},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5289521217346191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.512923002243042},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.49439263343811035},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4365314841270447},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.42539846897125244},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.4235055446624756},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3607335686683655},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2501712441444397},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20736154913902283},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17572584748268127},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14450570940971375},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0763055682182312},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tg.2022.3226526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2022.3226526","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Games","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.6899999976158142}],"awards":[{"id":"https://openalex.org/G3373226507","display_name":null,"funder_award_id":"62272497","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1625390266","https://openalex.org/W2006791053","https://openalex.org/W2103315867","https://openalex.org/W2106975967","https://openalex.org/W2155027007","https://openalex.org/W2248846161","https://openalex.org/W2257979135","https://openalex.org/W2574978968","https://openalex.org/W2736601468","https://openalex.org/W2741375793","https://openalex.org/W2765302304","https://openalex.org/W2803308811","https://openalex.org/W2807741983","https://openalex.org/W2902907165","https://openalex.org/W2960876848","https://openalex.org/W2964164283","https://openalex.org/W2965394063","https://openalex.org/W2972894440","https://openalex.org/W2979533262","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W2996896271","https://openalex.org/W3013828496","https://openalex.org/W3044994704","https://openalex.org/W3172924075","https://openalex.org/W4214717370","https://openalex.org/W4234761190","https://openalex.org/W4283815845","https://openalex.org/W4289360601","https://openalex.org/W4295598622","https://openalex.org/W4298857966","https://openalex.org/W4298876402","https://openalex.org/W6636578284","https://openalex.org/W6637967152","https://openalex.org/W6675509861","https://openalex.org/W6676175064","https://openalex.org/W6683204974","https://openalex.org/W6683300800","https://openalex.org/W6691217529","https://openalex.org/W6696772115","https://openalex.org/W6741002519","https://openalex.org/W6749304979","https://openalex.org/W6751629939","https://openalex.org/W6752380930","https://openalex.org/W6755963907","https://openalex.org/W6768884620","https://openalex.org/W6772005887","https://openalex.org/W6775289199","https://openalex.org/W6781244629","https://openalex.org/W6796814964"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2386410636","https://openalex.org/W2025663273","https://openalex.org/W3038962357","https://openalex.org/W4387019592","https://openalex.org/W4313679781","https://openalex.org/W3099153698","https://openalex.org/W3184322736"],"abstract_inverted_index":{"Although":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"has":[4],"achieved":[5],"great":[6,16],"success":[7],"in":[8,30,116,161,200],"diverse":[9],"scenarios,":[10],"complex":[11],"gambling":[12,44,57,135],"games":[13,58],"still":[14],"pose":[15],"challenges":[17],"for":[18,134,176],"RL.":[19],"Common":[20],"deep":[21,92],"RL":[22,93,198],"methods":[23,94],"have":[24],"difficulties":[25],"maintaining":[26],"stability":[27],"and":[28,75,120,140,204],"efficiency":[29,203],"such":[31],"games.":[32,136],"By":[33],"theoretical":[34],"analysis,":[35],"we":[36,128],"find":[37],"that":[38,192],"the":[39,66,73,82,97,100,104,107,117,153,158,173,195],"return":[40,54],"distribution":[41,55],"of":[42,50,56,99,106,157],"a":[43,88,112,121,131,145,185],"game":[45],"is":[46,59],"an":[47],"intrinsic":[48],"factor":[49],"this":[51,126],"problem.":[52],"Such":[53],"partitioned":[60],"into":[61],"two":[62,70],"parts,":[63],"depending":[64],"on":[65],"win/lose":[67],"outcome.":[68],"These":[69],"parts":[71],"represent":[72],"gain":[74],"loss.":[76],"They":[77],"repel":[78],"each":[79],"other":[80],"because":[81],"player":[83],"keeps":[84],"\u201craising,\u201d":[85],"i.e.,":[86],"making":[87],"wager.":[89],"However,":[90],"common":[91],"directly":[95],"approximate":[96],"expectation":[98],"return,":[101],"without":[102],"considering":[103],"particularity":[105],"distribution.":[108],"This":[109],"way":[110],"causes":[111],"redundant":[113,154],"loss":[114,155],"term":[115,156],"objective":[118,159],"function":[119,160],"subsequent":[122],"high":[123],"variance.":[124],"In":[125,163],"work,":[127],"propose":[129],"WagerWin,":[130],"new":[132],"framework":[133,151],"WagerWin":[137,165,193],"introduces":[138],"probability":[139],"value":[141,148],"factorization":[142],"to":[143],"construct":[144],"more":[146],"effective":[147],"function.":[149],"Our":[150],"removes":[152],"training.":[162],"addition,":[164],"supports":[166],"customized":[167],"policy":[168,175],"adaptation,":[169],"which":[170],"can":[171],"tune":[172],"pretrained":[174],"different":[177],"inclinations.":[178],"We":[179],"conduct":[180],"extensive":[181],"experiments":[182],"onDouDizhuand":[183],"SmallDou,":[184],"reduced":[186],"version":[187],"ofDouDizhu.":[188],"The":[189],"results":[190],"demonstrate":[191],"outperforms":[194],"original":[196],"state-of-the-art":[197],"model":[199],"both":[201],"training":[202],"stability.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}