{"id":"https://openalex.org/W4213191092","doi":"https://doi.org/10.5220/0010787500003116","title":"Augmenting Reinforcement Learning to Enhance Cooperation in the Iterated Prisoner\u2019s Dilemma","display_name":"Augmenting Reinforcement Learning to Enhance Cooperation in the Iterated Prisoner\u2019s Dilemma","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4213191092","doi":"https://doi.org/10.5220/0010787500003116"},"language":"en","primary_location":{"id":"doi:10.5220/0010787500003116","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010787500003116","pdf_url":null,"source":{"id":"https://openalex.org/S4363608837","display_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.5220/0010787500003116","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002177696","display_name":"Grace Feehan","orcid":"https://orcid.org/0000-0002-8629-1800"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Grace Feehan","raw_affiliation_strings":["Loughborough University, Epinal Way, Loughborough, U.K., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Loughborough University, Epinal Way, Loughborough, U.K., --- Select a Country ---","institution_ids":["https://openalex.org/I143804889"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011019780","display_name":"Shaheen Fatima","orcid":"https://orcid.org/0000-0002-6068-2942"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shaheen Fatima","raw_affiliation_strings":["Loughborough University, Epinal Way, Loughborough, U.K., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Loughborough University, Epinal Way, Loughborough, U.K., --- Select a Country ---","institution_ids":["https://openalex.org/I143804889"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I143804889"],"apc_list":null,"apc_paid":null,"fwci":2.7113,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.90111483,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"146","last_page":"157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.992900013923645,"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":0.992900013923645,"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/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9663000106811523,"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"}},{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.945900022983551,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/prisoners-dilemma","display_name":"Prisoner's dilemma","score":0.9195425510406494},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8263642191886902},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.7204867601394653},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6222438812255859},{"id":"https://openalex.org/keywords/iterated-function","display_name":"Iterated function","score":0.6174700856208801},{"id":"https://openalex.org/keywords/superrationality","display_name":"Superrationality","score":0.6147992610931396},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.46412137150764465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3617376685142517},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1992582380771637},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.13477060198783875},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11417034268379211}],"concepts":[{"id":"https://openalex.org/C113494165","wikidata":"https://www.wikidata.org/wiki/Q41693","display_name":"Prisoner's dilemma","level":3,"score":0.9195425510406494},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8263642191886902},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.7204867601394653},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6222438812255859},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.6174700856208801},{"id":"https://openalex.org/C90659851","wikidata":"https://www.wikidata.org/wiki/Q1300745","display_name":"Superrationality","level":4,"score":0.6147992610931396},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.46412137150764465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3617376685142517},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1992582380771637},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13477060198783875},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11417034268379211},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0010787500003116","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010787500003116","pdf_url":null,"source":{"id":"https://openalex.org/S4363608837","display_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/19208958","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Augmenting_reinforcement_learning_to_enhance_cooperation_in_the_iterated_prisoner_s_dilemma/19208958","pdf_url":null,"source":{"id":"https://openalex.org/S4306402585","display_name":"Loughborough University Research Repository (Loughborough University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I143804889","host_organization_name":"Loughborough University","host_organization_lineage":["https://openalex.org/I143804889"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"}],"best_oa_location":{"id":"doi:10.5220/0010787500003116","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010787500003116","pdf_url":null,"source":{"id":"https://openalex.org/S4363608837","display_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4299530539","https://openalex.org/W1829339509","https://openalex.org/W3122059234","https://openalex.org/W4380049051","https://openalex.org/W4387723278","https://openalex.org/W4385348898","https://openalex.org/W3149882248","https://openalex.org/W2004817889","https://openalex.org/W46230372","https://openalex.org/W1446198759"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"algorithms":[2],"applied":[3],"to":[4,11,59,88,189],"social":[5],"dilemmas":[6],"sometimes":[7],"struggle":[8],"with":[9,46],"converging":[10],"mutual":[12,42,150,181],"cooperation":[13,43,104,162],"against":[14],"like-minded":[15],"partners,":[16],"particularly":[17],"when":[18,44,154],"utilising":[19],"greedy":[20],"behavioural":[21,135],"selection":[22],"methods.":[23],"Recent":[24],"research":[25,50,139],"has":[26],"demonstrated":[27],"how":[28,93],"affective":[29],"cognitive":[30],"mechanisms,":[31],"such":[32],"as":[33,71],"mood":[34,159],"and":[35,121,128,145,160],"emotion,":[36],"might":[37,99],"facilitate":[38],"increased":[39,180],"rates":[40],"of":[41,75,78,103,126,149,158,164,173,185],"integrated":[45],"these":[47],"algorithms.":[48],"This":[49],"has,":[51],"thus":[52],"far,":[53],"primarily":[54],"utilised":[55],"mobile":[56],"multi-agent":[57],"frameworks":[58],"demonstrate":[60],"this":[61],"relationship":[62],"-":[63],"where":[64],"they":[65],"have":[66],"also":[67],"identified":[68],"interaction":[69,86],"structure":[70,87],"a":[72,83,94,111],"key":[73],"determinant":[74],"the":[76,101,106,124,129,147,156,161,165,171,177],"emergence":[77],"cooperation.":[79],"Here,":[80],"we":[81,115],"use":[82],"deterministic,":[84],"static":[85],"provide":[89],"deeper":[90],"insight":[91],"into":[92],"particular":[95],"moody":[96,174],"reinforcement":[97],"learner":[98],"encourage":[100],"evolution":[102],"in":[105,176],"Iterated":[107],"Prisoner\u2019s":[108],"Dilemma.":[109],"In":[110],"novel":[112],"grid":[113],"environment,":[114],"both":[116,155],"replicated":[117],"original":[118],"test":[119],"parameters":[120],"then":[122],"varied":[123],"distribution":[125],"agents":[127,175,188],"payoff":[130,166],"matrix.":[131],"We":[132],"found":[133],"that":[134,146],"trends":[136],"from":[137],"past":[138],"were":[140],"present":[141],"(with":[142],"suppressed":[143],"magnitude),":[144],"proportion":[148,172],"cooperations":[151,182],"was":[152],"heightened":[153],"influence":[157],"index":[163],"matrix":[167],"chosen":[168],"increased.":[169],"Changing":[170],"environment":[178],"only":[179],"by":[183],"virtue":[184],"introducing":[186],"cooperative":[187],"each":[190],"other.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}