{"id":"https://openalex.org/W4312954579","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892092","title":"Intrinsic Reward with Peer Incentives for Cooperative Multi-Agent Reinforcement Learning","display_name":"Intrinsic Reward with Peer Incentives for Cooperative Multi-Agent Reinforcement Learning","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312954579","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892092"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892092","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5074422885","display_name":"Tianle Zhang","orcid":"https://orcid.org/0000-0002-0779-5905"},"institutions":[{"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":true,"raw_author_name":"Tianle Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences,Beijing,China,100049"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412085","display_name":"Zhen Liu","orcid":"https://orcid.org/0000-0003-1610-2338"},"institutions":[{"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":"Zhen Liu","raw_affiliation_strings":["University of Chinese Academy of Sciences,Beijing,China,100049"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103000550","display_name":"Shiguang Wu","orcid":"https://orcid.org/0000-0001-9091-5236"},"institutions":[{"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":"Shiguang Wu","raw_affiliation_strings":["University of Chinese Academy of Sciences,Beijing,China,100049"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060319097","display_name":"Zhiqiang Pu","orcid":"https://orcid.org/0000-0002-4841-4048"},"institutions":[{"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":"Zhiqiang Pu","raw_affiliation_strings":["University of Chinese Academy of Sciences,Beijing,China,100049"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019541846","display_name":"Jianqiang Yi","orcid":"https://orcid.org/0000-0003-3268-9482"},"institutions":[{"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":"Jianqiang Yi","raw_affiliation_strings":["University of Chinese Academy of Sciences,Beijing,China,100049"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5074422885"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.1039,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.33274079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9606999754905701,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9589999914169312,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8553645610809326},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.7421669960021973},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7231391668319702},{"id":"https://openalex.org/keywords/incentive","display_name":"Incentive","score":0.6981669068336487},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5513895153999329},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5254644155502319},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44906559586524963},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43640202283859253},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4278339147567749},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4231891334056854},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.2648864984512329},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2375909686088562},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15355584025382996},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11332002282142639},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09229528903961182}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8553645610809326},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.7421669960021973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7231391668319702},{"id":"https://openalex.org/C29122968","wikidata":"https://www.wikidata.org/wiki/Q1414816","display_name":"Incentive","level":2,"score":0.6981669068336487},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5513895153999329},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5254644155502319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44906559586524963},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43640202283859253},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4278339147567749},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4231891334056854},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.2648864984512329},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2375909686088562},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15355584025382996},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11332002282142639},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09229528903961182},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892092","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G2369576154","display_name":null,"funder_award_id":"XDA27030204","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G2433199840","display_name":null,"funder_award_id":"2018AAA0101005,2018AAA0102402","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W560595466","https://openalex.org/W1191599655","https://openalex.org/W1981005934","https://openalex.org/W1997396773","https://openalex.org/W2486285194","https://openalex.org/W2582846779","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2736601468","https://openalex.org/W2747213132","https://openalex.org/W2785315072","https://openalex.org/W2894976951","https://openalex.org/W2902922568","https://openalex.org/W2949963774","https://openalex.org/W2970272688","https://openalex.org/W2997940961","https://openalex.org/W3030840723","https://openalex.org/W3037941652","https://openalex.org/W3100930738","https://openalex.org/W3127561923","https://openalex.org/W3169821733","https://openalex.org/W4288594419","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W6627932998","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6741002519","https://openalex.org/W6747941106","https://openalex.org/W6749304979","https://openalex.org/W6755069753","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6779753894","https://openalex.org/W6780396752","https://openalex.org/W6796684891"],"related_works":["https://openalex.org/W3201448254","https://openalex.org/W4286970243","https://openalex.org/W2066431708","https://openalex.org/W4384133558","https://openalex.org/W3025615835","https://openalex.org/W173210993","https://openalex.org/W2390660599","https://openalex.org/W2355932053","https://openalex.org/W2366296021","https://openalex.org/W2382571223"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,53,84],"novel":[6],"Intrinsic":[7],"Reward":[8],"method":[9,35],"with":[10,64],"Peer":[11],"Incentives":[12],"(IRPI)":[13],"to":[14,47,67,102,149],"promote":[15],"the":[16,23,65,73,79,94,97,104,108,111,119,122,139,146],"inter-agent":[17],"direct":[18],"interactions":[19],"and":[20,87,116],"implicitly":[21],"address":[22],"credit":[24],"assignment":[25],"problem":[26],"in":[27,129,133,158],"cooperative":[28,160],"multi-agent":[29],"reinforcement":[30],"learning":[31],"(MARL).":[32],"The":[33],"IRPI":[34,141],"can":[36,142],"build":[37],"mutual":[38],"incentives":[39],"between":[40,76,93,107],"agents":[41,109,148],"by":[42,71,89],"using":[43,72,90,110,124],"their":[44,49],"causal":[45,74,91,105],"effect,":[46],"realize":[48],"advanced":[50],"cooperation.":[51],"Specifically,":[52],"new":[54],"intrinsic":[55],"reward":[56,68],"mechanism":[57,80],"is":[58,81,100],"conducted,":[59],"which":[60],"equips":[61],"each":[62],"agent":[63,70],"ability":[66],"other":[69],"effect":[75,92,106,123],"them.":[77],"Moreover,":[78],"built":[82],"through":[83],"neural":[85],"network":[86],"learned":[88],"agents.":[95],"Furthermore,":[96],"counterfactual":[98],"reasoning":[99],"used":[101],"infer":[103],"joint":[112],"action-state":[113],"value":[114,127],"function,":[115],"then":[117],"assess":[118],"quality":[120],"of":[121],"individual":[125],"state":[126],"function":[128],"MARL.":[130],"Simulational":[131],"results":[132],"Starcraft":[134],"II":[135],"Micromanagement":[136],"demonstrate":[137],"that":[138],"proposed":[140],"enhance":[143],"cooperation":[144],"among":[145],"RL":[147],"achieve":[150],"better":[151],"performance":[152],"than":[153],"some":[154],"state-of-the-art":[155],"MARL":[156],"methods":[157],"various":[159],"multi-aaent":[161],"tasks.":[162]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}