{"id":"https://openalex.org/W4414110785","doi":"https://doi.org/10.1109/tnnls.2025.3598301","title":"When to Align: Dynamic Behavior Consistency for Multiagent Systems via Intrinsic Rewards","display_name":"When to Align: Dynamic Behavior Consistency for Multiagent Systems via Intrinsic Rewards","publication_year":2025,"publication_date":"2025-09-10","ids":{"openalex":"https://openalex.org/W4414110785","doi":"https://doi.org/10.1109/tnnls.2025.3598301","pmid":"https://pubmed.ncbi.nlm.nih.gov/40928917"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3598301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3598301","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5119587066","display_name":"Kunyang Lin","orcid":"https://orcid.org/0009-0001-2009-7693"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kunyang Lin","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367907","display_name":"Yufeng Wang","orcid":"https://orcid.org/0000-0001-8713-3153"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufeng Wang","raw_affiliation_strings":["School of Future Technology, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Future Technology, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004837552","display_name":"Peihao Chen","orcid":"https://orcid.org/0000-0002-6847-1621"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peihao Chen","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018498977","display_name":"Runhao Zeng","orcid":"https://orcid.org/0000-0001-8694-4245"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runhao Zeng","raw_affiliation_strings":["Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102831936","display_name":"Yinjie Lei","orcid":"https://orcid.org/0000-0001-6856-3342"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I24201400","display_name":"Chengdu University of Information Technology","ror":"https://ror.org/01yxwrh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I24201400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinjie Lei","raw_affiliation_strings":["College of Electronics and Information Engineering, Sichuan University, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Sichuan University, Chengdu, China","institution_ids":["https://openalex.org/I24201400","https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029080973","display_name":"Siyuan Zhou","orcid":"https://orcid.org/0000-0001-7822-2381"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Siyuan Zhou","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Sai Kung, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Sai Kung, Hong Kong","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090234226","display_name":"Qing Du","orcid":"https://orcid.org/0000-0002-8411-6734"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Du","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032352025","display_name":"Mingkui Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingkui Tan","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040877128","display_name":"Chuang Gan","orcid":"https://orcid.org/0000-0003-4031-5886"},"institutions":[{"id":"https://openalex.org/I177605424","display_name":"Amherst College","ror":"https://ror.org/028vqfs63","country_code":"US","type":"education","lineage":["https://openalex.org/I177605424"]},{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuang Gan","raw_affiliation_strings":["UMass Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"UMass Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5119587066"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12362108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"12","first_page":"20105","last_page":"20119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8833000063896179,"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":0.8833000063896179,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.871399998664856,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.6671000123023987},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5024999976158142},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.3756999969482422},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.36660000681877136},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.3508000075817108}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7339000105857849},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6671000123023987},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5024999976158142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42719998955726624},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.3756999969482422},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2581999897956848},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.25679999589920044}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3598301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3598301","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40928917","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40928917","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2500617447","display_name":null,"funder_award_id":"U24A20327","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4860469773","display_name":null,"funder_award_id":"62202311","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5986993592","display_name":null,"funder_award_id":"2024ZDZX3012","funder_id":"https://openalex.org/F4320326279","funder_display_name":"Department of Education of Guangdong Province"},{"id":"https://openalex.org/G657063301","display_name":null,"funder_award_id":"2023A1515011512","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326279","display_name":"Department of Education of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W2012812921","https://openalex.org/W2056716515","https://openalex.org/W2084238990","https://openalex.org/W2091565802","https://openalex.org/W2160141417","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2810602713","https://openalex.org/W2991046523","https://openalex.org/W2997502221","https://openalex.org/W3040507763","https://openalex.org/W3040973413","https://openalex.org/W3041202696","https://openalex.org/W3131448887","https://openalex.org/W3166816823","https://openalex.org/W3175224103","https://openalex.org/W3192815666","https://openalex.org/W3207654079","https://openalex.org/W3210096323","https://openalex.org/W3211583675","https://openalex.org/W4200635426","https://openalex.org/W4213246061","https://openalex.org/W4226257065","https://openalex.org/W4282944715","https://openalex.org/W4309349085","https://openalex.org/W4309367642","https://openalex.org/W4379622577","https://openalex.org/W4388470074","https://openalex.org/W4388878401","https://openalex.org/W4389179347","https://openalex.org/W4393160115","https://openalex.org/W4394627306","https://openalex.org/W4409581282","https://openalex.org/W4410115220","https://openalex.org/W4411086446"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0,117],"multiagent":[1],"systems,":[2],"learning":[3,168],"optimal":[4,169],"behavior":[5,74],"policies":[6],"for":[7],"individual":[8],"agents":[9,29,50,85,92,109,136],"remains":[10],"a":[11,45,121],"challenging":[12],"yet":[13],"crucial":[14],"task.":[15],"While":[16],"recent":[17],"research":[18],"has":[19],"made":[20],"strides":[21],"in":[22,110,167],"this":[23],"area,":[24],"the":[25,77,80,87,140],"issue":[26],"of":[27,61,96,142],"when":[28,112],"should":[30,57],"maintain":[31],"consistent":[32,144],"behaviors":[33,56],"with":[34,59],"one":[35],"another":[36],"is":[37,148],"still":[38],"not":[39],"adequately":[40],"addressed.":[41],"This":[42],"article":[43],"proposes":[44],"novel":[46],"approach":[47],"to":[48,51,68,93,113,137],"enable":[49],"autonomously":[52],"decide":[53,139],"whether":[54],"their":[55,62,70,115],"align":[58],"those":[60],"peers":[63],"by":[64,83],"leveraging":[65],"intrinsic":[66,104],"rewards":[67],"optimize":[69],"policies.":[71,170],"We":[72],"define":[73],"consistency":[75],"as":[76],"divergence":[78],"between":[79],"actions":[81],"taken":[82],"two":[84],"given":[86],"same":[88],"observations.":[89],"To":[90],"encourage":[91],"be":[94],"aware":[95],"each":[97,132],"other's":[98],"behaviors,":[99],"we":[100,119],"propose":[101],"dynamic":[102,122],"consistency-based":[103],"reward":[105],"(DCIR),":[106],"which":[107],"guides":[108],"determining":[111],"synchronize":[114],"behaviors.":[116],"addition,":[118],"introduce":[120],"scaling":[123,129],"network":[124],"(DSN)":[125],"that":[126],"provides":[127],"learnable":[128],"factors":[130],"at":[131],"time":[133],"step,":[134],"enabling":[135],"dynamically":[138],"extent":[141],"rewarding":[143],"behavior.":[145],"Our":[146],"method":[147],"evaluated":[149],"on":[150],"environments":[151],"including":[152],"Multiagent":[153],"Particle,":[154],"Google":[155],"Research":[156],"Football,":[157],"and":[158],"StarCraft":[159],"II":[160],"Micromanagement.":[161],"Experimental":[162],"results":[163],"demonstrate":[164],"its":[165],"effectiveness":[166]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}