{"id":"https://openalex.org/W4416014022","doi":"https://doi.org/10.1609/aiide.v21i1.36838","title":"Minding Motivation: The Effect of Intrinsic Motivation on Agent Behaviors","display_name":"Minding Motivation: The Effect of Intrinsic Motivation on Agent Behaviors","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416014022","doi":"https://doi.org/10.1609/aiide.v21i1.36838"},"language":null,"primary_location":{"id":"doi:10.1609/aiide.v21i1.36838","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aiide.v21i1.36838","pdf_url":"https://ojs.aaai.org/index.php/AIIDE/article/download/36838/38976","source":{"id":"https://openalex.org/S4387284112","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","issn_l":"2326-909X","issn":["2326-909X","2334-0924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ojs.aaai.org/index.php/AIIDE/article/download/36838/38976","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049902028","display_name":"Leonardo Villalobos-Arias","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leonardo Villalobos-Arias","raw_affiliation_strings":["North Carolina State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003208640","display_name":"Grant C. Forbes","orcid":"https://orcid.org/0009-0009-5858-4276"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grant Forbes","raw_affiliation_strings":["North Carolina State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085043351","display_name":"Jianxun Wang","orcid":"https://orcid.org/0000-0002-9030-1733"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianxun Wang","raw_affiliation_strings":["North Carolina State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012351691","display_name":"David L. Roberts","orcid":"https://orcid.org/0000-0001-7872-4840"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David L. Roberts","raw_affiliation_strings":["North Carolina State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004340848","display_name":"Arnav Jhala","orcid":"https://orcid.org/0000-0003-3874-1720"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arnav Jhala","raw_affiliation_strings":["North Carolina State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29214832,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":"1","first_page":"347","last_page":"356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7985000014305115,"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":0.7985000014305115,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.09139999747276306,"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"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.015599999576807022,"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":0.5920000076293945},{"id":"https://openalex.org/keywords/intrinsic-motivation","display_name":"Intrinsic motivation","score":0.5864999890327454},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5383999943733215},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4982999861240387},{"id":"https://openalex.org/keywords/reward-system","display_name":"Reward system","score":0.4318999946117401},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3869999945163727}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.6717000007629395},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5920000076293945},{"id":"https://openalex.org/C2985564149","wikidata":"https://www.wikidata.org/wiki/Q644302","display_name":"Intrinsic motivation","level":2,"score":0.5864999890327454},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5383999943733215},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.5048999786376953},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4982999861240387},{"id":"https://openalex.org/C143661069","wikidata":"https://www.wikidata.org/wiki/Q670713","display_name":"Reward system","level":2,"score":0.4318999946117401},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3894999921321869},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C86844869","wikidata":"https://www.wikidata.org/wiki/Q2798820","display_name":"Hacker","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C14262774","wikidata":"https://www.wikidata.org/wiki/Q4880695","display_name":"Behavior change","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C68784500","wikidata":"https://www.wikidata.org/wiki/Q1570691","display_name":"Adaptive behavior","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C29122968","wikidata":"https://www.wikidata.org/wiki/Q1414816","display_name":"Incentive","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C64948172","wikidata":"https://www.wikidata.org/wiki/Q1653277","display_name":"Brain stimulation reward","level":4,"score":0.2563999891281128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aiide.v21i1.36838","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aiide.v21i1.36838","pdf_url":"https://ojs.aaai.org/index.php/AIIDE/article/download/36838/38976","source":{"id":"https://openalex.org/S4387284112","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","issn_l":"2326-909X","issn":["2326-909X","2334-0924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aiide.v21i1.36838","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aiide.v21i1.36838","pdf_url":"https://ojs.aaai.org/index.php/AIIDE/article/download/36838/38976","source":{"id":"https://openalex.org/S4387284112","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","issn_l":"2326-909X","issn":["2326-909X","2334-0924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323217","display_name":"Universidad de Costa Rica","ror":"https://ror.org/02yzgww51"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416014022.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Games":[0],"are":[1,15],"challenging":[2],"for":[3,51],"Reinforcement":[4],"Learning":[5],"(RL)":[6],"agents":[7],"due":[8],"to":[9,34,78,81,135],"their":[10],"reward":[11,35,54,68,133,163],"sparsity,":[12],"as":[13,44],"rewards":[14,85],"only":[16],"obtainable":[17],"after":[18],"long":[19],"sequences":[20],"of":[21,58,89,105],"deliberate":[22],"actions.":[23],"Intrinsic":[24],"Motivation":[25],"(IM)":[26],"methods\u2014which":[27],"introduce":[28],"exploration":[29],"rewards\u2014are":[30],"an":[31,41],"effective":[32],"solution":[33],"sparsity.":[36],"However,":[37],"IM":[38,84,107,117,142],"also":[39,152],"causes":[40,143],"issue":[42],"known":[43],"\u2018reward":[45],"hacking\u2019,":[46],"where":[47],"the":[48,52,56,61,87,101,110,148,154,156],"agent":[49,157],"optimizes":[50],"new":[53],"at":[55],"expense":[57],"properly":[59],"playing":[60],"game.":[62],"The":[63],"larger":[64],"problem":[65],"is":[66,71,75],"that":[67,126,141,160],"hacking":[69,164],"itself":[70],"largely":[72],"unknown;":[73],"there":[74],"no":[76],"answer":[77],"whether,":[79],"and":[80,159],"what":[82],"extent,":[83],"change":[86,145],"behavior":[88,104],"RL":[90],"agents.":[91],"This":[92],"study":[93],"takes":[94],"a":[95,124],"first":[96],"step":[97],"by":[98,146],"empirically":[99],"evaluating":[100],"impact":[102],"on":[103,109],"three":[106],"techniques":[108],"MiniGrid":[111],"game-like":[112],"environment.":[113],"We":[114],"compare":[115],"these":[116],"models":[118],"with":[119,130],"Generalized":[120],"Reward":[121],"Matching":[122],"(GRM),":[123],"method":[125],"can":[127],"be":[128],"used":[129],"any":[131],"intrinsic":[132],"function":[134],"guarantee":[136],"optimality.":[137],"Our":[138],"results":[139],"suggest":[140],"noticeable":[144],"increasing":[147],"initial":[149],"rewards,":[150],"but":[151],"altering":[153],"way":[155],"plays,":[158],"GRM":[161],"mitigated":[162],"in":[165],"some":[166],"scenarios.":[167]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-07T00:00:00"}