{"id":"https://openalex.org/W2965163470","doi":"https://doi.org/10.24963/ijcai.2019/65","title":"Value Function Transfer for Deep Multi-Agent Reinforcement Learning Based on N-Step Returns","display_name":"Value Function Transfer for Deep Multi-Agent Reinforcement Learning Based on N-Step Returns","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2965163470","doi":"https://doi.org/10.24963/ijcai.2019/65","mag":"2965163470"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/65","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/65","pdf_url":"https://www.ijcai.org/proceedings/2019/0065.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0065.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014714438","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0003-3314-1750"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]},{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Fuxi AI Lab in Netease","National Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab in Netease","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104264364","display_name":"Yujing Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujing Hu","raw_affiliation_strings":["Fuxi AI Lab in Netease"],"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab in Netease","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074250521","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-2488-1813"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103121632","display_name":"Yingfeng Chen","orcid":"https://orcid.org/0000-0002-9747-5947"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingfeng Chen","raw_affiliation_strings":["Fuxi AI Lab in Netease"],"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab in Netease","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022008180","display_name":"Changjie Fan","orcid":"https://orcid.org/0000-0001-5420-0516"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changjie Fan","raw_affiliation_strings":["Fuxi AI Lab in Netease"],"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab in Netease","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5014714438"],"corresponding_institution_ids":["https://openalex.org/I4210091137","https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":1.7341,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.88739798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"457","last_page":"463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.995199978351593,"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"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9801999926567078,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8046325445175171},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7334083914756775},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6355264186859131},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5947482585906982},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5631595253944397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5626691579818726},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.503851592540741},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48495009541511536},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4246193468570709},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41583260893821716},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.38670963048934937},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3550502061843872},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3483491539955139},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.18184566497802734},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14305520057678223}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8046325445175171},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7334083914756775},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6355264186859131},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5947482585906982},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5631595253944397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5626691579818726},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.503851592540741},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48495009541511536},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4246193468570709},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41583260893821716},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.38670963048934937},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3550502061843872},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3483491539955139},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.18184566497802734},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14305520057678223},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2019/65","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/65","pdf_url":"https://www.ijcai.org/proceedings/2019/0065.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/65","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/65","pdf_url":"https://www.ijcai.org/proceedings/2019/0065.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7211685174","display_name":null,"funder_award_id":"6143200","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2965163470.pdf","grobid_xml":"https://content.openalex.org/works/W2965163470.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W11035765","https://openalex.org/W168445157","https://openalex.org/W1591992921","https://openalex.org/W2054339854","https://openalex.org/W2096622112","https://openalex.org/W2118318536","https://openalex.org/W2128814508","https://openalex.org/W2138965998","https://openalex.org/W2145339207","https://openalex.org/W2153427071","https://openalex.org/W2160041839","https://openalex.org/W2400387077","https://openalex.org/W2464736835","https://openalex.org/W2604283518","https://openalex.org/W2617547828","https://openalex.org/W2736601468","https://openalex.org/W2807741983","https://openalex.org/W2964043796","https://openalex.org/W2964338167","https://openalex.org/W3011120880","https://openalex.org/W4295598622","https://openalex.org/W4299802797"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W2156021013","https://openalex.org/W2016648086","https://openalex.org/W4399157305","https://openalex.org/W3105579180","https://openalex.org/W1574958246"],"abstract_inverted_index":{"Many":[0],"real-world":[1],"problems,":[2],"such":[3],"as":[4,13],"robot":[5],"control":[6],"and":[7,57,117,133,150],"soccer":[8],"game,":[9],"are":[10],"naturally":[11],"modeled":[12],"sparse-interaction":[14],"multi-agent":[15,21,30,129,147],"systems.":[16],"Reutilizing":[17],"single-agent":[18],"knowledge":[19,48,104],"in":[20,125],"systems":[22],"with":[23],"sparse":[24],"interactions":[25],"can":[26,144],"greatly":[27],"accelerate":[28,146],"the":[29,87,92,141],"learning":[31,74,149],"process.":[32],"Previous":[33],"works":[34],"rely":[35],"on":[36,77,91,108],"bisimulation":[37,51],"metric":[38,52],"to":[39,55],"define":[40],"Markov":[41],"decision":[42],"process":[43],"(MDP)":[44],"similarity":[45,81,89],"for":[46,61],"controlling":[47],"transfer.":[49,121],"However,":[50],"is":[53,58],"costly":[54],"compute":[56],"not":[59],"suitable":[60],"high-dimensional":[62],"state":[63],"space":[64],"problems.":[65],"In":[66],"this":[67],"work,":[68],"we":[69,101],"propose":[70,102],"more":[71],"scalable":[72],"transfer":[73,105,116],"methods":[75,106,143],"based":[76,90,107],"a":[78],"novel":[79],"MDP":[80,88],"concept.":[82],"We":[83,122],"start":[84],"by":[85],"defining":[86],"N-step":[93],"return":[94],"(NSR)":[95],"values":[96],"of":[97],"an":[98],"MDP.":[99],"Then,":[100],"two":[103],"deep":[109],"neural":[110],"networks":[111],"called":[112],"direct":[113],"value":[114,119],"function":[115,120],"NSR-based":[118],"conduct":[123],"experiments":[124],"image-based":[126],"grid":[127],"world,":[128],"particle":[130],"environment":[131],"(MPE)":[132],"Ms.":[134],"Pac-Man":[135],"game.":[136],"The":[137],"results":[138],"indicate":[139],"that":[140],"proposed":[142],"significantly":[145],"reinforcement":[148],"meanwhile":[151],"get":[152],"better":[153],"asymptotic":[154],"performance.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}