{"id":"https://openalex.org/W4401990275","doi":"https://doi.org/10.1109/tg.2024.3450475","title":"Learning Individual Potential-Based Rewards in Multiagent Reinforcement Learning","display_name":"Learning Individual Potential-Based Rewards in Multiagent Reinforcement Learning","publication_year":2024,"publication_date":"2024-08-29","ids":{"openalex":"https://openalex.org/W4401990275","doi":"https://doi.org/10.1109/tg.2024.3450475"},"language":"en","primary_location":{"id":"doi:10.1109/tg.2024.3450475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2024.3450475","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/A5000473001","display_name":"Chen Yang","orcid":"https://orcid.org/0000-0001-9105-4087"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Yang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences and Center for Research on Intelligent System and Engineering, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9105-4087","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences and Center for Research on Intelligent System and Engineering, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101814011","display_name":"Pei Xu","orcid":"https://orcid.org/0000-0003-1766-5634"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pei Xu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences and Center for Research on Intelligent System and Engineering, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1766-5634","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences and Center for Research on Intelligent System and Engineering, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109012644","display_name":"Junge Zhang","orcid":"https://orcid.org/0000-0002-9970-394X"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junge Zhang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences and Center for Research on Intelligent System and Engineering, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9970-394X","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences and Center for Research on Intelligent System and Engineering, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11346929,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"2","first_page":"334","last_page":"345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.41350001096725464,"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":0.41350001096725464,"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":0.7102541923522949},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6415506601333618},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45173296332359314},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.4114440977573395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3871595859527588},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.36568206548690796},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3318008780479431},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.1895991861820221}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7102541923522949},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6415506601333618},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45173296332359314},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.4114440977573395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3871595859527588},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36568206548690796},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3318008780479431},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1895991861820221}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tg.2024.3450475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2024.3450475","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":[{"id":"https://metadata.un.org/sdg/10","score":0.4699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2371091044","https://openalex.org/W2171010636","https://openalex.org/W87513465","https://openalex.org/W2391666574","https://openalex.org/W2786230833","https://openalex.org/W3203256658","https://openalex.org/W2352650970","https://openalex.org/W1544514152","https://openalex.org/W1493952344","https://openalex.org/W4312372616"],"abstract_inverted_index":{"A":[0],"great":[1],"challenge":[2],"for":[3,50,67,110,119,181],"applying":[4],"multiagent":[5],"reinforcement":[6],"learning":[7],"(MARL)":[8],"in":[9,126],"the":[10,58,65,72,127,139,144,155,166,173,185,191],"field":[11],"of":[12,57,202],"game":[13,94,214,230],"artificial":[14],"intelligence":[15],"(AI)":[16],"is":[17,42,136,147,158,188],"to":[18,21,25,52,122,148,159],"enable":[19],"agents":[20,51],"learn":[22,114],"diversified":[23],"policies":[24,74,150],"handle":[26],"different":[27,93],"game-specific":[28],"problems,":[29],"while":[30],"receiving":[31],"only":[32],"a":[33,39,101,115,200],"shared":[34],"team":[35],"reward.":[36],"At":[37],"present,":[38],"common":[40],"approach":[41],"reward":[43,68],"shaping,":[44],"which":[45],"focuses":[46],"on":[47,64,85,207],"designing":[48],"rewards":[49,88,109,125,176],"guide":[53],"cooperation.":[54],"However,":[55],"most":[56],"existing":[59,203],"methods":[60,82,206,226],"require":[61],"prior":[62],"knowledge":[63],"environment":[66,167],"design":[69],"or":[70],"alter":[71],"optimal":[73],"after":[75],"imposing":[76],"extra":[77],"rewards.":[78],"Besides,":[79],"previous":[80],"MARL":[81,103,193,205],"that":[83,105,172,184,219,232],"rely":[84],"manually":[86],"designed":[87],"can":[89,177],"hardly":[90],"generalize":[91],"across":[92],"environments.":[95,215],"To":[96],"this":[97],"end,":[98],"we":[99,113],"propose":[100],"new":[102],"method":[104,198,222],"learns":[106],"individual":[107,124,174],"potential-based":[108,152,175],"agents.":[111],"Specifically,":[112],"parameterized":[116,161],"potential":[117,162],"function":[118],"each":[120],"agent":[121],"generate":[123],"discounted":[128],"temporal":[129],"difference":[130],"form.":[131],"The":[132],"whole":[133],"update":[134],"procedure":[135],"modeled":[137],"as":[138],"bilevel":[140],"optimization":[141,186],"problem,":[142],"where":[143],"lower":[145],"level":[146,157],"optimize":[149,160],"with":[151,190,199],"rewards,":[153],"and":[154,209,227,236],"upper":[156],"functions":[163],"toward":[164],"maximizing":[165],"return.":[168],"We":[169,195],"theoretically":[170],"prove":[171],"guarantee":[178],"policy":[179],"invariance":[180],"agents,":[182],"so":[183],"objective":[187],"consistent":[189],"original":[192],"problem.":[194],"evaluate":[196],"our":[197,220],"number":[201],"state-of-the-art":[204],"predator\u2013prey":[208],"<italic":[210],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[211],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">StarCraft":[212],"II</i>":[213],"Empirical":[216],"results":[217],"show":[218],"proposed":[221],"significantly":[223],"outperforms":[224],"baseline":[225],"achieves":[228],"better":[229],"AI":[231],"enjoys":[233],"high":[234],"performance":[235],"generalization.":[237]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}