{"id":"https://openalex.org/W4412446221","doi":"https://doi.org/10.1109/cogsima64436.2025.11079473","title":"Innate-Values-Driven Reinforcement Learning Based Cognitive Modeling","display_name":"Innate-Values-Driven Reinforcement Learning Based Cognitive Modeling","publication_year":2025,"publication_date":"2025-06-02","ids":{"openalex":"https://openalex.org/W4412446221","doi":"https://doi.org/10.1109/cogsima64436.2025.11079473"},"language":"en","primary_location":{"id":"doi:10.1109/cogsima64436.2025.11079473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cogsima64436.2025.11079473","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":2.6579,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91042423,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"127","last_page":"134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9972000122070312,"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":0.9972000122070312,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9470999836921692,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7746070623397827},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6518620848655701},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43234843015670776},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.41837847232818604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2942524552345276},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14588427543640137},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12268397212028503},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.07783034443855286}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7746070623397827},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6518620848655701},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43234843015670776},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.41837847232818604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2942524552345276},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14588427543640137},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12268397212028503},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.07783034443855286},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cogsima64436.2025.11079473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cogsima64436.2025.11079473","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W157606319","https://openalex.org/W1595483645","https://openalex.org/W1863227302","https://openalex.org/W1935925708","https://openalex.org/W1995335544","https://openalex.org/W2034806191","https://openalex.org/W2114424330","https://openalex.org/W2145339207","https://openalex.org/W2151954045","https://openalex.org/W2188721763","https://openalex.org/W2480255888","https://openalex.org/W2503173364","https://openalex.org/W2511444485","https://openalex.org/W2599823115","https://openalex.org/W2646827645","https://openalex.org/W2736601468","https://openalex.org/W2963871073","https://openalex.org/W2963948533","https://openalex.org/W2969456553","https://openalex.org/W3112882278","https://openalex.org/W3124613582","https://openalex.org/W3196654803","https://openalex.org/W4233840023","https://openalex.org/W4253795049","https://openalex.org/W4285009743","https://openalex.org/W4379620277","https://openalex.org/W4391436304","https://openalex.org/W6628902087","https://openalex.org/W6634481309","https://openalex.org/W6635465357","https://openalex.org/W6685444567","https://openalex.org/W6692846177","https://openalex.org/W6741002519","https://openalex.org/W6766694020"],"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":{"Innate":[0],"values":[1],"describe":[2],"agents'":[3,53],"intrinsic":[4],"motivations,":[5],"which":[6,57],"reflect":[7],"their":[8,25,64],"inherent":[9],"interests":[10],"and":[11,16,66,85,105,110,135,149,158,171],"preferences":[12],"for":[13,99],"pursuing":[14],"goals":[15],"drive":[17],"them":[18,162],"to":[19,102,139],"develop":[20],"diverse":[21],"skills":[22],"that":[23,185],"satisfy":[24],"various":[26,195],"needs.":[27],"Traditional":[28],"reinforcement":[29,178],"learning":[30,33,101,179],"(RL)":[31],"is":[32,95],"from":[34,60],"interaction":[35],"based":[36,62,88,130],"on":[37,63,89,131],"the":[38,42,48,72,113,145,174,186,191],"feedback":[39],"rewards":[40,49],"of":[41],"environment.":[43],"However,":[44],"in":[45,92,112,144,173],"real":[46],"scenarios,":[47],"are":[50],"generated":[51],"by":[52],"innate":[54],"value":[55],"systems,":[56],"differ":[58],"vastly":[59],"individuals":[61,100],"needs":[65,91],"requirements.":[67],"In":[68],"other":[69],"words,":[70],"considering":[71],"AI":[73],"agent":[74,192],"as":[75,167],"a":[76,96,122],"self-organizing":[77],"system,":[78],"developing":[79],"its":[80,90,141],"awareness":[81],"through":[82,147],"balancing":[83],"internal":[84],"external":[86],"utilities":[87],"different":[93],"tasks":[94],"crucial":[97],"problem":[98],"support":[103],"others":[104],"integrate":[106],"community":[107],"with":[108,163],"safety":[109],"harmony":[111],"long":[114],"term.":[115],"To":[116],"address":[117],"this":[118],"gap,":[119],"we":[120,152,183],"propose":[121],"new":[123],"RL":[124,128],"model":[125],"termed":[126],"innate-values-driven":[127],"(IVRL)":[129],"combined":[132],"motivations'":[133],"models":[134,188],"expected":[136],"utility":[137],"theory":[138],"mimic":[140],"complex":[142],"behaviors":[143],"evolution":[146],"decision-making":[148],"learning.":[150],"Then,":[151],"introduce":[153],"two":[154],"IVRL-based":[155,187],"models:":[156],"IV-DQN":[157],"IV-A2C.":[159],"By":[160],"comparing":[161],"benchmark":[164],"algorithms":[165],"such":[166],"DQN,":[168],"DDQN,":[169],"A2C,":[170],"PPO":[172],"Role-Playing":[175],"Game":[176],"(RPG)":[177],"test":[180],"platform":[181],"VIZDoom,":[182],"demonstrated":[184],"can":[189],"help":[190],"rationally":[193],"organize":[194],"needs,":[196],"achieve":[197],"better":[198],"performance":[199],"effectively.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}