{"id":"https://openalex.org/W4412446163","doi":"https://doi.org/10.1109/cogsima64436.2025.11079504","title":"Innate-Values-Driven Reinforcement Learning Based Cooperative Multi-Agent Cognitive Modeling","display_name":"Innate-Values-Driven Reinforcement Learning Based Cooperative Multi-Agent Cognitive Modeling","publication_year":2025,"publication_date":"2025-06-02","ids":{"openalex":"https://openalex.org/W4412446163","doi":"https://doi.org/10.1109/cogsima64436.2025.11079504"},"language":"en","primary_location":{"id":"doi:10.1109/cogsima64436.2025.11079504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cogsima64436.2025.11079504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA)","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/A5020303837","display_name":"Qin Yang","orcid":"https://orcid.org/0000-0001-5342-1798"},"institutions":[{"id":"https://openalex.org/I24648388","display_name":"Bradley University","ror":"https://ror.org/04kmeaw70","country_code":"US","type":"education","lineage":["https://openalex.org/I24648388"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qin Yang","raw_affiliation_strings":["Bradley University,Intelligent Social Systems and Swarm Robotics Lab (ISR),Computer Science and Information Systems Department,Peoria,USA"],"affiliations":[{"raw_affiliation_string":"Bradley University,Intelligent Social Systems and Swarm Robotics Lab (ISR),Computer Science and Information Systems Department,Peoria,USA","institution_ids":["https://openalex.org/I24648388"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5020303837"],"corresponding_institution_ids":["https://openalex.org/I24648388"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24934795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"177","last_page":"181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.19519999623298645,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.19519999623298645,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12805","display_name":"Cognitive Science and Mapping","score":0.18940000236034393,"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":0.8332435488700867},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6648060083389282},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5573851466178894},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.4342173933982849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3175159692764282},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10471701622009277},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.061897069215774536}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8332435488700867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6648060083389282},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5573851466178894},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.4342173933982849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3175159692764282},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10471701622009277},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.061897069215774536},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cogsima64436.2025.11079504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cogsima64436.2025.11079504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1863227302","https://openalex.org/W1935925708","https://openalex.org/W2113476921","https://openalex.org/W2151954045","https://openalex.org/W2161061197","https://openalex.org/W2511444485","https://openalex.org/W2617547828","https://openalex.org/W2971634072","https://openalex.org/W3112882278","https://openalex.org/W3176265013","https://openalex.org/W4241414120","https://openalex.org/W4251942513","https://openalex.org/W4253795049","https://openalex.org/W6634481309","https://openalex.org/W6684660688","https://openalex.org/W6729587437","https://openalex.org/W6738796088","https://openalex.org/W6758846586","https://openalex.org/W6766805167"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"In":[0],"multi-agent":[1],"systems":[2],"(MAS),":[3],"the":[4,17,29,66,73,105,109,139,153,159,177],"dynamic":[5,123],"interaction":[6],"among":[7],"multiple":[8],"decision-makers":[9],"is":[10,87],"driven":[11],"by":[12],"their":[13,55,85,96,135],"innate":[14,32],"values,":[15],"affecting":[16],"environment's":[18],"state,":[19],"and":[20,40,45,52,58,76,79,98,127],"can":[21],"cause":[22],"specific":[23,43],"behavioral":[24],"patterns":[25],"to":[26,48,71,94,120,175,180],"emerge.":[27],"On":[28],"other":[30],"hand,":[31],"values":[33],"in":[34,62,84,104,134,164],"cognitive":[35],"modeling":[36],"reflect":[37],"individual":[38,131,154],"interests":[39],"preferences":[41,155],"for":[42,91,125],"tasks":[44],"drive":[46],"them":[47],"develop":[49],"diverse":[50],"skills":[51],"plans,":[53],"satisfying":[54],"various":[56],"needs":[57,83,132],"achieving":[59],"common":[60],"goals":[61],"cooperation.":[63,136],"Therefore,":[64],"building":[65],"awareness":[67],"of":[68],"AI":[69],"agents":[70],"balance":[72],"group":[74,81],"utilities":[75],"system":[77],"costs":[78],"meet":[80],"members'":[82],"cooperation":[86],"a":[88,116,144],"crucial":[89],"problem":[90],"individuals":[92],"learning":[93,113,128,149],"support":[95],"community":[97],"even":[99],"integrate":[100],"into":[101],"human":[102],"society":[103],"long":[106],"term.":[107],"However,":[108],"current":[110],"MAS":[111,146],"reinforcement":[112,148],"domain":[114],"lacks":[115],"general":[117,145],"intrinsic":[118],"model":[119],"describe":[121],"agents'":[122],"motivation":[124],"decision-making":[126],"from":[129,152],"an":[130],"perspective":[133],"To":[137],"address":[138],"gap,":[140],"this":[141],"paper":[142],"proposes":[143],"innate-values":[147],"(IVRL)":[150],"architecture":[151],"angle.":[156],"We":[157],"tested":[158],"Multi-Agent":[160,167],"IVRL":[161],"Actor-Critic":[162],"Model":[163],"different":[165],"StarCraft":[166],"Challenge":[168],"(SMAC)":[169],"settings,":[170],"which":[171],"demonstrated":[172],"its":[173],"potential":[174],"organize":[176],"group's":[178],"behaviours":[179],"achieve":[181],"better":[182],"performance.":[183]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}