{"id":"https://openalex.org/W4385764866","doi":"https://doi.org/10.24963/ijcai.2023/36","title":"Modeling Moral Choices in Social Dilemmas with Multi-Agent Reinforcement Learning","display_name":"Modeling Moral Choices in Social Dilemmas with Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385764866","doi":"https://doi.org/10.24963/ijcai.2023/36"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/36","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/36","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://cris.unibo.it/bitstream/11585/960141/2/0036.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071648490","display_name":"Elizaveta Tennant","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Elizaveta Tennant","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082771661","display_name":"Stephen Hailes","orcid":"https://orcid.org/0000-0001-7375-3642"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stephen Hailes","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078886343","display_name":"Mirco Musolesi","orcid":"https://orcid.org/0000-0001-9712-4090"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]},{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["GB","IT"],"is_corresponding":false,"raw_author_name":"Mirco Musolesi","raw_affiliation_strings":["University College London","University of Bologna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"University of Bologna","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.104,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.97208663,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"317","last_page":"325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12520","display_name":"Psychology of Moral and Emotional Judgment","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7284610867500305},{"id":"https://openalex.org/keywords/morality","display_name":"Morality","score":0.6779645085334778},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.6400758028030396},{"id":"https://openalex.org/keywords/social-cognitive-theory-of-morality","display_name":"Social cognitive theory of morality","score":0.5299072265625},{"id":"https://openalex.org/keywords/social-dilemma","display_name":"Social dilemma","score":0.5132009983062744},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4986443519592285},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4545899033546448},{"id":"https://openalex.org/keywords/moral-disengagement","display_name":"Moral disengagement","score":0.4142951965332031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3941636085510254},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.36254459619522095},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3073354959487915},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.29207485914230347}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7284610867500305},{"id":"https://openalex.org/C200113983","wikidata":"https://www.wikidata.org/wiki/Q48324","display_name":"Morality","level":2,"score":0.6779645085334778},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.6400758028030396},{"id":"https://openalex.org/C26918590","wikidata":"https://www.wikidata.org/wiki/Q7550991","display_name":"Social cognitive theory of morality","level":3,"score":0.5299072265625},{"id":"https://openalex.org/C187206662","wikidata":"https://www.wikidata.org/wiki/Q55607920","display_name":"Social dilemma","level":2,"score":0.5132009983062744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4986443519592285},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4545899033546448},{"id":"https://openalex.org/C57996006","wikidata":"https://www.wikidata.org/wiki/Q6909105","display_name":"Moral disengagement","level":2,"score":0.4142951965332031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3941636085510254},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.36254459619522095},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3073354959487915},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.29207485914230347},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2023/36","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/36","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.unibo.it:11585/960141","is_oa":true,"landing_page_url":"https://hdl.handle.net/11585/960141","pdf_url":"https://cris.unibo.it/bitstream/11585/960141/2/0036.pdf","source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:cris.unibo.it:11585/960141","is_oa":true,"landing_page_url":"https://hdl.handle.net/11585/960141","pdf_url":"https://cris.unibo.it/bitstream/11585/960141/2/0036.pdf","source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385764866.pdf"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1572298076","https://openalex.org/W1577983756","https://openalex.org/W1990066099","https://openalex.org/W1996197821","https://openalex.org/W2028753574","https://openalex.org/W2042848677","https://openalex.org/W2053616263","https://openalex.org/W2085728653","https://openalex.org/W2087322096","https://openalex.org/W2119432837","https://openalex.org/W2139612737","https://openalex.org/W2234474721","https://openalex.org/W2260046031","https://openalex.org/W2462906003","https://openalex.org/W2566902129","https://openalex.org/W2594794854","https://openalex.org/W2601920874","https://openalex.org/W2738240325","https://openalex.org/W2762221702","https://openalex.org/W2823329128","https://openalex.org/W2896252141","https://openalex.org/W2914351253","https://openalex.org/W2950993296","https://openalex.org/W2980061931","https://openalex.org/W2997338169","https://openalex.org/W3002916673","https://openalex.org/W3034612759","https://openalex.org/W3037042691","https://openalex.org/W3132138270","https://openalex.org/W3188288352","https://openalex.org/W4200375625","https://openalex.org/W4210389853","https://openalex.org/W4226483723","https://openalex.org/W4287870504","https://openalex.org/W4294656596","https://openalex.org/W4295150809","https://openalex.org/W4297783250"],"related_works":["https://openalex.org/W2393306073","https://openalex.org/W2038045674","https://openalex.org/W2393526026","https://openalex.org/W2368279538","https://openalex.org/W2372801241","https://openalex.org/W4378376832","https://openalex.org/W2387323919","https://openalex.org/W1968995485","https://openalex.org/W1557599030","https://openalex.org/W2896678408"],"abstract_inverted_index":{"Practical":[0],"uses":[1],"of":[2,14,37,77,80,92,106,132,135,201,204,209,224,230],"Artificial":[3],"Intelligence":[4],"(AI)":[5],"in":[6,60,95,184,233],"the":[7,12,75,107,199,207,215,222,228],"real":[8],"world":[9],"have":[10,22],"demonstrated":[11],"importance":[13],"embedding":[15],"moral":[16,93,119,143,182,231],"choices":[17,108],"into":[18],"intelligent":[19],"agents.":[20,62],"They":[21],"also":[23],"highlighted":[24],"that":[25,67,85,127,146],"defining":[26],"top-down":[27],"ethical":[28,58,137],"constraints":[29],"on":[30,118,156,206],"AI":[31,61],"according":[32,87],"to":[33,88,123],"any":[34],"one":[35],"type":[36],"morality":[38,154,205],"is":[39,74],"extremely":[40],"challenging":[41],"and":[42,56,70,150,162,165,194,214,235],"can":[43],"pose":[44],"risks.":[45],"A":[46],"bottom-up":[47],"learning":[48,181],"approach":[49,174],"may":[50],"be":[51],"more":[52],"appropriate":[53],"for":[54,227],"studying":[55],"developing":[57],"behavior":[59,79],"In":[63,98],"particular,":[64],"we":[65,101,140,171,220],"believe":[66],"an":[68],"interesting":[69],"insightful":[71],"starting":[72],"point":[73],"analysis":[76,105],"emergent":[78],"Reinforcement":[81],"Learning":[82],"(RL)":[83],"agents":[84,113,183,232],"act":[86],"a":[89,103,133],"predefined":[90],"set":[91,134],"rewards":[94,115],"social":[96,187,217],"dilemmas.":[97],"this":[99],"work,":[100],"present":[102],"systematic":[104],"made":[109],"by":[110,175],"intrinsically-motivated":[111],"RL":[112],"whose":[114],"are":[116,128],"based":[117,155],"theories.":[120],"We":[121,197],"aim":[122],"design":[124],"reward":[125,144],"structures":[126],"simplified":[129],"yet":[130],"representative":[131],"key":[136],"systems.":[138],"Therefore,":[139],"first":[141],"define":[142],"functions":[145],"distinguish":[147],"between":[148,153,163,180],"consequence-":[149],"norm-based":[151],"agents,":[152],"societal":[157],"norms":[158],"or":[159,212],"internal":[160],"virtues,":[161],"single-":[164],"mixed-virtue":[166],"(e.g.,":[167],"multi-objective)":[168],"methodologies.":[169],"Then,":[170],"evaluate":[172],"our":[173],"modeling":[176],"repeated":[177],"dyadic":[178],"interactions":[179],"three":[185],"iterated":[186],"dilemma":[188],"games":[189],"(Prisoner's":[190],"Dilemma,":[191],"Volunteer's":[192],"Dilemma":[193],"Stag":[195],"Hunt).":[196],"analyze":[198],"impact":[200],"different":[202],"types":[203],"emergence":[208],"cooperation,":[210],"defection":[211],"exploitation,":[213],"corresponding":[216],"outcomes.":[218],"Finally,":[219],"discuss":[221],"implications":[223],"these":[225],"findings":[226],"development":[229],"artificial":[234],"mixed":[236],"human-AI":[237],"societies.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}