{"id":"https://openalex.org/W4396941579","doi":"https://doi.org/10.1109/tai.2024.3401649","title":"Bidirectional Influence and Interaction for Multiagent Reinforcement Learning","display_name":"Bidirectional Influence and Interaction for Multiagent Reinforcement Learning","publication_year":2024,"publication_date":"2024-05-15","ids":{"openalex":"https://openalex.org/W4396941579","doi":"https://doi.org/10.1109/tai.2024.3401649"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2024.3401649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2024.3401649","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","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/A5114778037","display_name":"Shaoqi Sun","orcid":"https://orcid.org/0009-0005-9656-6918"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoqi Sun","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0005-9656-6918","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013340793","display_name":"Kele Xu","orcid":"https://orcid.org/0000-0001-5997-5169"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kele Xu","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-5997-5169","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039795290","display_name":"Dawei Feng","orcid":"https://orcid.org/0000-0002-7587-8905"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Feng","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-7587-8905","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088885490","display_name":"Bo Ding","orcid":"https://orcid.org/0000-0002-1236-8318"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ding","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-1236-8318","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.7269,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7476215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"5","issue":"10","first_page":"4984","last_page":"4995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.31189998984336853,"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":0.31189998984336853,"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","display_name":"Reinforcement","score":0.7044203281402588},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6578735709190369},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4833638072013855},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35651710629463196},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.27735045552253723},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23889213800430298},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.13261306285858154}],"concepts":[{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.7044203281402588},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6578735709190369},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4833638072013855},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35651710629463196},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27735045552253723},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23889213800430298},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13261306285858154}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2024.3401649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2024.3401649","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"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 Artificial Intelligence","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":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G4459954457","display_name":null,"funder_award_id":"2021ZD0112904","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"}],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1777239053","https://openalex.org/W1818863960","https://openalex.org/W1976195538","https://openalex.org/W1994005439","https://openalex.org/W2026653933","https://openalex.org/W2037067712","https://openalex.org/W2085946266","https://openalex.org/W2104641222","https://openalex.org/W2736601468","https://openalex.org/W2908261578","https://openalex.org/W2945442007","https://openalex.org/W2963762747","https://openalex.org/W2965163470","https://openalex.org/W2982316857","https://openalex.org/W3006049620","https://openalex.org/W3043075313","https://openalex.org/W3106539628","https://openalex.org/W3121341741","https://openalex.org/W3121342653","https://openalex.org/W3170473100","https://openalex.org/W3173477571","https://openalex.org/W3179088773","https://openalex.org/W4214717370","https://openalex.org/W4313679571","https://openalex.org/W4317832225","https://openalex.org/W4381712751","https://openalex.org/W4388328811","https://openalex.org/W4392883051","https://openalex.org/W6627932998","https://openalex.org/W6638088447","https://openalex.org/W6638331262","https://openalex.org/W6736572398","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6762491519","https://openalex.org/W6766805167","https://openalex.org/W6771876938","https://openalex.org/W6779101081","https://openalex.org/W6784463116","https://openalex.org/W6789076383","https://openalex.org/W6791129655","https://openalex.org/W6797584944","https://openalex.org/W6797930488","https://openalex.org/W6840380725","https://openalex.org/W6848308608","https://openalex.org/W6848770789","https://openalex.org/W6853911056","https://openalex.org/W6858565513"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588"],"abstract_inverted_index":{"In":[0,36],"recent":[1],"years,":[2],"Multi-Agent":[3],"Reinforcement":[4],"Learning":[5],"(MARL)":[6],"has":[7],"demonstrated":[8],"considerable":[9],"potential":[10,275],"across":[11],"diverse":[12],"applications.":[13],"However,":[14],"in":[15,92,114,165,202,238,245,280],"reinforcement":[16,297],"learning":[17,63,72,226],"environments":[18],"characterized":[19],"by":[20],"sparse":[21,166],"rewards,":[22,47,222],"the":[23,62,70,78,85,96,110,119,156,174,194,203,215,234,240,263,274,277,282,294],"scarcity":[24],"of":[25,74,80,121,159,197,205,211,218,236,242,276,285,296],"reward":[26,32,160,167,198,206,243,255],"signals":[27],"may":[28],"give":[29],"rise":[30],"to":[31,42,44,132,135,154,193,221],"conflicts":[33,161,244],"among":[34,90,162,184],"agents.":[35],"these":[37,212],"scenarios,":[38],"each":[39],"agent":[40],"tend":[41],"compete":[43],"obtain":[45],"limited":[46],"deviating":[48],"from":[49,109],"collaborative":[50,111,283],"efforts":[51],"aimed":[52],"at":[53],"achieving":[54,268],"collective":[55],"team":[56,81,265],"objectives.":[57],"This":[58,104,150,271],"not":[59],"only":[60],"amplifies":[61],"challenge":[64,241],"but":[65],"also":[66],"imposes":[67],"constraints":[68],"on":[69],"overall":[71],"performance":[73],"agents,":[75],"ultimately":[76],"compromising":[77],"attainment":[79],"goals.":[82],"To":[83],"mitigate":[84],"conflicting":[86],"competition":[87],"for":[88,292],"rewards":[89,139],"agents":[91,134,163,179,185,259],"MARL,":[93],"we":[94,232],"introduce":[95],"Bi-directional":[97],"Influence":[98],"and":[99,124],"Interaction":[100],"(BDII)":[101],"MARL":[102],"framework.":[103],"innovative":[105],"approach":[106],"draws":[107],"inspiration":[108],"ethos":[112],"observed":[113],"human":[115],"social":[116],"cooperation,":[117],"specifically":[118],"concept":[120,128],"\u201csharing":[122],"joys":[123],"sorrows.\u201d":[125],"The":[126,188,209],"fundamental":[127],"behind":[129],"BDII":[130,169,237,252],"is":[131],"empower":[133],"share":[136],"their":[137],"individual":[138],"with":[140,262],"collaborators,":[141],"fostering":[142],"a":[143,224,289],"cooperative":[144,225],"rather":[145],"than":[146],"competitive":[147],"behavioral":[148],"paradigm.":[149],"strategic":[151],"shift":[152],"aims":[153],"resolve":[155],"pervasive":[157],"issue":[158],"operating":[164],"environments.":[168],"incorporates":[170],"two":[171,189],"key":[172],"factors\u2014namely,":[173],"Gaussian":[175],"kernel":[176],"distance":[177],"between":[178],"(physical":[180],"distance),":[181],"policy":[182],"diversity":[183],"(logical":[186],"distance).":[187],"factor":[190],"collectively":[191],"contribute":[192],"dynamic":[195],"adjustment":[196],"allocation":[199],"coefficients,":[200],"culminating":[201],"formation":[204],"distribution":[207],"weights.":[208],"incorporation":[210],"weights":[213],"facilitates":[214],"equitable":[216],"sharing":[217],"agents\u2019":[219],"contributions":[220],"promoting":[223],"environment.":[227],"Through":[228],"extensive":[229],"experimental":[230],"evaluations,":[231],"substantiate":[233],"efficacy":[235],"addressing":[239],"MARL.":[246],"Our":[247],"research":[248],"findings":[249],"affirm":[250],"that":[251,258],"significantly":[253],"mitigates":[254],"conflicts,":[256],"ensuring":[257],"consistently":[260],"align":[261],"original":[264],"objectives,":[266],"thereby":[267],"state-of-the-art":[269],"performance.":[270],"validation":[272],"underscores":[273],"proposed":[278],"framework":[279],"enhancing":[281],"nature":[284],"multi-agent":[286],"systems,":[287],"offering":[288],"promising":[290],"avenue":[291],"advancing":[293],"field":[295],"learning.":[298]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}