{"id":"https://openalex.org/W7131838687","doi":"https://doi.org/10.5555/3635637.3663196","title":"Fairness and Cooperation between Independent Reinforcement Learners through Indirect Reciprocity","display_name":"Fairness and Cooperation between Independent Reinforcement Learners through Indirect Reciprocity","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7131838687","doi":"https://doi.org/10.5555/3635637.3663196"},"language":"en","primary_location":{"id":"pmh:oai:dare.uva.nl:openaire/804c9937-bf39-43f6-b54b-24bd47c09ca4","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/fairness-and-cooperation-between-independent-reinforcement-learners-through-indirect-reciprocity(804c9937-bf39-43f6-b54b-24bd47c09ca4).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Smit, J & Santos, F P 2024, Fairness and Cooperation between Independent Reinforcement Learners through Indirect Reciprocity. in AAMAS '24 : Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems : May 6-10, 2024, Auckland, New Zealand. Richland, SC, pp. 2468-2470, 23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024, Auckland, New Zealand, 6/05/24. < https://dl.acm.org/doi/10.5555/3635637.3663196 >","raw_type":"info:eu-repo/semantics/publishedVersion"},"type":"article","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://handle.uba.uva.nl/personal/pure/en/publications/fairness-and-cooperation-between-independent-reinforcement-learners-through-indirect-reciprocity(804c9937-bf39-43f6-b54b-24bd47c09ca4).html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127314804","display_name":"Jacobus; id_orcid 0000-0001-5466-1259 Smit","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Smit, Jacobus; id_orcid 0000-0001-5466-1259","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127065851","display_name":"Fernando P. Santos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Santos, Fernando P.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74685605,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.6470999717712402,"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":0.6470999717712402,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.06729999929666519,"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/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.06440000236034393,"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/reciprocity","display_name":"Reciprocity (cultural anthropology)","score":0.7699000239372253},{"id":"https://openalex.org/keywords/reputation","display_name":"Reputation","score":0.753000020980835},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5189999938011169},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5012000203132629},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.46160000562667847},{"id":"https://openalex.org/keywords/social-learning","display_name":"Social learning","score":0.44920000433921814},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4253999888896942},{"id":"https://openalex.org/keywords/social-dilemma","display_name":"Social dilemma","score":0.3668999969959259}],"concepts":[{"id":"https://openalex.org/C169903001","wikidata":"https://www.wikidata.org/wiki/Q3264987","display_name":"Reciprocity (cultural anthropology)","level":2,"score":0.7699000239372253},{"id":"https://openalex.org/C48798503","wikidata":"https://www.wikidata.org/wiki/Q877546","display_name":"Reputation","level":2,"score":0.753000020980835},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.541100025177002},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5012000203132629},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.46160000562667847},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.459199994802475},{"id":"https://openalex.org/C79416737","wikidata":"https://www.wikidata.org/wiki/Q2305519","display_name":"Social learning","level":2,"score":0.44920000433921814},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.44760000705718994},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4253999888896942},{"id":"https://openalex.org/C187206662","wikidata":"https://www.wikidata.org/wiki/Q55607920","display_name":"Social dilemma","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C130064352","wikidata":"https://www.wikidata.org/wiki/Q853725","display_name":"Social relation","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.3167000114917755},{"id":"https://openalex.org/C29122968","wikidata":"https://www.wikidata.org/wiki/Q1414816","display_name":"Incentive","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C158608086","wikidata":"https://www.wikidata.org/wiki/Q2990613","display_name":"Prosocial behavior","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.28360000252723694},{"id":"https://openalex.org/C162222271","wikidata":"https://www.wikidata.org/wiki/Q92779871","display_name":"Public good","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C52820260","wikidata":"https://www.wikidata.org/wiki/Q7551312","display_name":"Social preferences","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C2780279448","wikidata":"https://www.wikidata.org/wiki/Q2559380","display_name":"Altruism (biology)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.27230000495910645},{"id":"https://openalex.org/C549774020","wikidata":"https://www.wikidata.org/wiki/Q851147","display_name":"Welfare economics","level":1,"score":0.2685999870300293},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.257999986410141},{"id":"https://openalex.org/C31250377","wikidata":"https://www.wikidata.org/wiki/Q1509670","display_name":"Strong reciprocity","level":4,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:dare.uva.nl:openaire/804c9937-bf39-43f6-b54b-24bd47c09ca4","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/fairness-and-cooperation-between-independent-reinforcement-learners-through-indirect-reciprocity(804c9937-bf39-43f6-b54b-24bd47c09ca4).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Smit, J & Santos, F P 2024, Fairness and Cooperation between Independent Reinforcement Learners through Indirect Reciprocity. in AAMAS '24 : Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems : May 6-10, 2024, Auckland, New Zealand. Richland, SC, pp. 2468-2470, 23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024, Auckland, New Zealand, 6/05/24. < https://dl.acm.org/doi/10.5555/3635637.3663196 >","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:dare.uva.nl:openaire/804c9937-bf39-43f6-b54b-24bd47c09ca4","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/fairness-and-cooperation-between-independent-reinforcement-learners-through-indirect-reciprocity(804c9937-bf39-43f6-b54b-24bd47c09ca4).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Smit, J & Santos, F P 2024, Fairness and Cooperation between Independent Reinforcement Learners through Indirect Reciprocity. in AAMAS '24 : Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems : May 6-10, 2024, Auckland, New Zealand. Richland, SC, pp. 2468-2470, 23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024, Auckland, New Zealand, 6/05/24. < https://dl.acm.org/doi/10.5555/3635637.3663196 >","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.41086968779563904,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,59],"a":[1,30,64,97],"multi-agent":[2],"setting,":[3],"altruistic":[4],"cooperation":[5,35,91,119],"is":[6],"costly":[7],"yet":[8],"socially":[9],"desirable.":[10],"As":[11],"such,":[12],"agents":[13,45,103],"adapting":[14],"through":[15],"independent":[16,101],"reinforcement":[17],"learning":[18,125],"struggle":[19],"to":[20,22,33,82,87,130,138],"converge":[21],"efficient,":[23],"cooperative":[24],"policies.":[25],"Indirect":[26],"reciprocity":[27],"(IR)":[28],"constitutes":[29],"possible":[31],"mechanism":[32],"encourage":[34],"by":[36],"introducing":[37],"reputations,":[38],"social":[39,78,107],"norms":[40,79,113,128],"and":[41,71,74,92,120],"the":[42],"possibility":[43],"that":[44,66,111],"reciprocate":[46],"based":[47],"on":[48],"past":[49],"actions.":[50],"IR":[51],"has":[52],"been":[53],"mainly":[54],"studied":[55],"in":[56,122],"homogeneous":[57],"populations.":[58],"this":[60],"paper,":[61],"we":[62],"introduce":[63],"model":[65],"allows":[67],"for":[68],"both":[69,118],"reputation":[70],"group-based":[72],"cooperation,":[73],"analyse":[75],"how":[76,96],"specific":[77],"(i.e.":[80],"rules":[81],"assign":[83],"reputations)":[84],"can":[85,136],"lead":[86,137],"varying":[88],"levels":[89],"of":[90,100,124],"fairness.":[93],"We":[94,109],"investigate":[95],"finite":[98],"population":[99],"Q-learning":[102],"perform":[104],"under":[105],"different":[106],"norms.":[108],"observe":[110],"while":[112],"such":[114],"as":[115],"Stern-Judging":[116],"sustain":[117],"fairness":[121],"populations":[123],"agents,":[126],"other":[127],"used":[129],"judge":[131],"in-":[132],"or":[133],"out-group":[134],"interactions":[135],"unfair":[139],"outcomes.":[140]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-28T00:00:00"}