{"id":"https://openalex.org/W3187188159","doi":"https://doi.org/10.24963/ijcai.2021/492","title":"Boosting Offline Reinforcement Learning with Residual Generative Modeling","display_name":"Boosting Offline Reinforcement Learning with Residual Generative Modeling","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3187188159","doi":"https://doi.org/10.24963/ijcai.2021/492","mag":"3187188159"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/492","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/492","pdf_url":"https://www.ijcai.org/proceedings/2021/0492.pdf","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0492.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100777770","display_name":"Hua Wei","orcid":"https://orcid.org/0000-0002-3735-1635"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Wei","raw_affiliation_strings":["Tencent AI Lab","Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073681676","display_name":"Deheng Ye","orcid":"https://orcid.org/0000-0002-1754-1837"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deheng Ye","raw_affiliation_strings":["Tencent AI Lab","Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364709","display_name":"Zhao Liu","orcid":"https://orcid.org/0000-0002-0673-3235"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Liu","raw_affiliation_strings":["Tencent AI Lab","Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102921136","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0002-8738-3942"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wu","raw_affiliation_strings":["Tencent AI Lab","Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032061647","display_name":"Bo Yuan","orcid":"https://orcid.org/0000-0003-2169-0007"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Yuan","raw_affiliation_strings":["Tencent AI Lab","Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032254756","display_name":"Qiang Fu","orcid":"https://orcid.org/0000-0002-1456-4216"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Fu","raw_affiliation_strings":["Tencent AI Lab","Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100613522","display_name":"Wei Yang","orcid":"https://orcid.org/0000-0001-8460-3121"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Yang","raw_affiliation_strings":["Tencent AI Lab","Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016516907","display_name":"Zhenhui Li","orcid":"https://orcid.org/0000-0001-7221-2588"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenhui Li","raw_affiliation_strings":["The Pennsylvania State University","The Pennsylvania State University, University Park, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University, University Park, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4396,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61388473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3574","last_page":"3580"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9883000254631042,"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":0.9620000123977661,"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":0.8915321826934814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.717827558517456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6298555135726929},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6175718307495117},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6168235540390015},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.6160733699798584},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5866192579269409},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.584234356880188},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5779625177383423},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.526454746723175},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.461590051651001},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43919646739959717},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.4248831272125244},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2848399579524994},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22291401028633118},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20286110043525696},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16502133011817932},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.09967121481895447}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8915321826934814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717827558517456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6298555135726929},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6175718307495117},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6168235540390015},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.6160733699798584},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5866192579269409},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.584234356880188},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5779625177383423},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.526454746723175},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.461590051651001},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43919646739959717},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.4248831272125244},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2848399579524994},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22291401028633118},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20286110043525696},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16502133011817932},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.09967121481895447},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/492","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/492","pdf_url":"https://www.ijcai.org/proceedings/2021/0492.pdf","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/492","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/492","pdf_url":"https://www.ijcai.org/proceedings/2021/0492.pdf","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3187188159.pdf","grobid_xml":"https://content.openalex.org/works/W3187188159.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1931877416","https://openalex.org/W2108598243","https://openalex.org/W2138909795","https://openalex.org/W2142641780","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2166302491","https://openalex.org/W2766447205","https://openalex.org/W2781726626","https://openalex.org/W2797993462","https://openalex.org/W2904453761","https://openalex.org/W2904730732","https://openalex.org/W2947150733","https://openalex.org/W2963864421","https://openalex.org/W2964323789","https://openalex.org/W2991355586","https://openalex.org/W2996037775","https://openalex.org/W2996896271","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3033324992","https://openalex.org/W3096726323","https://openalex.org/W3107951310","https://openalex.org/W3178094535","https://openalex.org/W4288363736","https://openalex.org/W4298857966","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W2944746750","https://openalex.org/W1501190258","https://openalex.org/W4256087190","https://openalex.org/W4240668504","https://openalex.org/W2788366696","https://openalex.org/W3188865574","https://openalex.org/W2011233848","https://openalex.org/W2125074935","https://openalex.org/W2569146624","https://openalex.org/W2155027007"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2,33],"(RL)":[3],"tries":[4],"to":[5,94],"learn":[6,108,128],"the":[7,34,43,49,58,64,80,122,138],"near-optimal":[8],"policy":[9,27,96,111],"with":[10],"recorded":[11],"offline":[12,17,100,124],"experience":[13],"without":[14],"online":[15,140],"exploration.Current":[16],"RL":[18,125],"research":[19,40],"includes:":[20],"1)":[21],"generative":[22,70,83,92],"modeling,":[23],"i.e.,":[24],"approximating":[25],"a":[26,90],"using":[28],"fixed":[29],"data;":[30],"and":[31],"2)":[32],"state-action":[35,44],"value":[36,53],"function.":[37],"While":[38],"most":[39],"focuses":[41],"on":[42],"function":[45,54],"part":[46],"through":[47],"reducing":[48],"bootstrapping":[50],"error":[51,67,81,98],"in":[52,69,82,113,133],"approximation":[55,97],"induced":[56],"by":[57],"distribution":[59],"shift":[60],"of":[61,66,146],"training":[62],"data,":[63],"effects":[65],"propagation":[68],"modeling":[71],"have":[72],"been":[73],"neglected.":[74],"In":[75,117],"this":[76],"paper,":[77],"we":[78,119],"analyze":[79],"modeling.":[84],"We":[85,102],"propose":[86],"AQL":[87],"(action-conditioned":[88],"Q-learning),":[89],"residual":[91],"model":[93],"reduce":[95],"for":[99],"RL.":[101],"show":[103,120],"that":[104,121],"our":[105],"method":[106,126],"can":[107,127],"more":[109,129],"accurate":[110],"approximations":[112],"different":[114],"benchmark":[115],"datasets.":[116],"addition,":[118],"proposed":[123],"competitive":[130],"AI":[131],"agents":[132],"complex":[134],"control":[135],"tasks":[136],"under":[137],"multiplayer":[139],"battle":[141],"arena":[142],"(MOBA)":[143],"game,":[144],"Honor":[145],"Kings.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}