{"id":"https://openalex.org/W4361802167","doi":"https://doi.org/10.1109/tg.2023.3263013","title":"Attention-Based Intrinsic Reward Mixing Network for Credit Assignment in Multiagent Reinforcement Learning","display_name":"Attention-Based Intrinsic Reward Mixing Network for Credit Assignment in Multiagent Reinforcement Learning","publication_year":2023,"publication_date":"2023-03-29","ids":{"openalex":"https://openalex.org/W4361802167","doi":"https://doi.org/10.1109/tg.2023.3263013"},"language":"en","primary_location":{"id":"doi:10.1109/tg.2023.3263013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2023.3263013","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/A5100318314","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-9235-9429"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Li","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-9235-9429","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115592188","display_name":"Weiyan Liu","orcid":"https://orcid.org/0009-0000-7016-1430"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiyan Liu","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073038991","display_name":"Shitong Shao","orcid":"https://orcid.org/0000-0003-4689-6140"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shitong Shao","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0003-4689-6140","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067258924","display_name":"Shiyi Huang","orcid":"https://orcid.org/0009-0001-9134-0259"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyi Huang","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048327458","display_name":"Aiguo Song","orcid":"https://orcid.org/0000-0002-1982-6780"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aiguo Song","raw_affiliation_strings":["School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-1982-6780","affiliations":[{"raw_affiliation_string":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100318314"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":2.2153,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89929254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"16","issue":"2","first_page":"270","last_page":"281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9036999940872192,"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":0.9036999940872192,"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":0.7715716361999512},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5939837694168091},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.5313166975975037},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.49840521812438965},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3781821131706238},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12296929955482483}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7715716361999512},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5939837694168091},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.5313166975975037},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.49840521812438965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3781821131706238},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12296929955482483},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tg.2023.3263013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2023.3263013","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":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G8715754740","display_name":null,"funder_award_id":"20200058069001","funder_id":"https://openalex.org/F4320322857","funder_display_name":"Aeronautical Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320322857","display_name":"Aeronautical Science Foundation of China","ror":"https://ror.org/02wq41p38"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W1641379095","https://openalex.org/W2119717200","https://openalex.org/W2125487757","https://openalex.org/W2583993537","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2749604329","https://openalex.org/W2780799698","https://openalex.org/W2783558323","https://openalex.org/W2810602713","https://openalex.org/W2884001105","https://openalex.org/W2888100907","https://openalex.org/W2899829828","https://openalex.org/W2904483377","https://openalex.org/W2908261578","https://openalex.org/W2953461088","https://openalex.org/W2963369679","https://openalex.org/W2964319688","https://openalex.org/W2973229164","https://openalex.org/W2982316857","https://openalex.org/W3008337835","https://openalex.org/W3016931720","https://openalex.org/W3019166713","https://openalex.org/W3044015199","https://openalex.org/W3100789280","https://openalex.org/W3127561923","https://openalex.org/W3156829097","https://openalex.org/W3210096323","https://openalex.org/W3212386989","https://openalex.org/W4214717370","https://openalex.org/W4226292595","https://openalex.org/W4312822248","https://openalex.org/W6623517193","https://openalex.org/W6637967152","https://openalex.org/W6712181171","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6749304979","https://openalex.org/W6755069753","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6767151588","https://openalex.org/W6767327128","https://openalex.org/W6769462197","https://openalex.org/W6772005887","https://openalex.org/W6781750019","https://openalex.org/W6849773618"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W1987513656","https://openalex.org/W2072376847","https://openalex.org/W2089013912"],"abstract_inverted_index":{"Credit":[0],"assignment":[1,75,187],"is":[2,25],"a":[3,34,64,81,104,116],"critical":[4],"problem":[5],"in":[6,76,93,115,150],"cooperative":[7],"Multi-Agent":[8],"Reinforcement":[9],"Learning":[10],"(MARL).":[11],"To":[12],"address":[13],"this":[14,60],"problem,":[15],"current":[16],"studies":[17],"mainly":[18],"rely":[19],"on":[20,86,136,174],"the":[21,29,45,52,87,90,97,110,125,129,132,137,147,153,166,178,185],"intrinsic":[22,41,83,111,168],"reward,":[23],"which":[24],"directly":[26],"summed":[27],"with":[28,184],"global":[30],"reward":[31,42,84,127,169],"to":[32,95,123,128,170,177],"generate":[33],"total":[35,126],"reward.":[36],"However,":[37],"such":[38],"kinds":[39],"of":[40,56,89,99,131,140,152],"functions":[43],"ignore":[44],"dependence":[46],"among":[47],"agents":[48],"and":[49,54,112,118,158],"inevitably":[50],"limit":[51],"adaptivity":[53],"effectiveness":[55,98],"MARL":[57],"methods.":[58],"In":[59],"paper,":[61],"we":[62,79,102],"propose":[63],"novel":[65],"method,":[66],"Attention-based":[67],"Intrinsic":[68],"Reward":[69],"Mixing":[70],"Network":[71],"(AIRMN),":[72],"for":[73],"credit":[74,186],"MARL.":[77],"Specifically,":[78],"design":[80],"new":[82,105],"network":[85,107],"basis":[88],"attention":[91],"mechanism,":[92],"order":[94],"enhance":[96],"teamwork.":[100],"Besides,":[101],"devise":[103],"mixing":[106],"that":[108,144,161],"combines":[109],"extrinsic":[113],"rewards":[114],"nonlinear":[117],"dynamic":[119],"manner,":[120],"so":[121],"as":[122],"adapt":[124],"variation":[130],"environment.":[133],"Experimental":[134],"results":[135],"battle":[138],"games":[139],"StarCraft":[141],"II":[142],"demonstrate":[143],"AIRMN":[145,162],"outperforms":[146],"state-of-the-art":[148],"methods":[149],"terms":[151],"average":[154],"test":[155],"win":[156],"rate,":[157],"also":[159],"validate":[160],"can":[163],"dynamically":[164],"return":[165],"precise":[167],"each":[171],"agent":[172],"based":[173],"their":[175],"contributions":[176],"team":[179],"cooperation,":[180],"thereby":[181],"better":[182],"dealing":[183],"problem.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}