{"id":"https://openalex.org/W7137903061","doi":"https://doi.org/10.1609/aaai.v40i35.40194","title":"Learning to Cooperate with Minimal Observability","display_name":"Learning to Cooperate with Minimal Observability","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137903061","doi":"https://doi.org/10.1609/aaai.v40i35.40194"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i35.40194","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i35.40194","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i35.40194","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129727653","display_name":"Chin-wing Leung","orcid":null},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chin-wing Leung","raw_affiliation_strings":["University of Warwick"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Warwick","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129653556","display_name":"Paolo Turrini","orcid":null},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paolo Turrini","raw_affiliation_strings":["University of Warwick"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Warwick","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129661632","display_name":"Fernando P. Santos","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Fernando P. Santos","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129714160","display_name":"Mirco Musolesi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210097606","display_name":"GNA University","ror":"https://ror.org/00cy7e479","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210097606"]},{"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","IN"],"is_corresponding":false,"raw_author_name":"Mirco Musolesi","raw_affiliation_strings":["University College London, University of London\nUniversity of Bologna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London, University of London\nUniversity of Bologna","institution_ids":["https://openalex.org/I45129253","https://openalex.org/I4210097606"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":0.25446429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"35","first_page":"29521","last_page":"29529"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.888700008392334,"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":0.888700008392334,"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/T12090","display_name":"Language and cultural evolution","score":0.02500000037252903,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"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":0.019200000911951065,"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/observability","display_name":"Observability","score":0.758400022983551},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.5924999713897705},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.588699996471405},{"id":"https://openalex.org/keywords/social-learning","display_name":"Social learning","score":0.5374000072479248},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5163999795913696},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4004000127315521},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.38119998574256897},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.37119999527931213}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.758400022983551},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.626800000667572},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.5924999713897705},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.588699996471405},{"id":"https://openalex.org/C79416737","wikidata":"https://www.wikidata.org/wiki/Q2305519","display_name":"Social learning","level":2,"score":0.5374000072479248},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5163999795913696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40610000491142273},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.3091999888420105},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3050000071525574},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C187206662","wikidata":"https://www.wikidata.org/wiki/Q55607920","display_name":"Social dilemma","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2597000002861023},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i35.40194","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i35.40194","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/40194","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/40194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i35.40194","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i35.40194","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.44590526819229126,"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":{"Cooperation":[0],"among":[1,180],"independent":[2],"learning":[3,58,146,169],"agents":[4,20,60,76],"is":[5],"desirable":[6],"as":[7,48,107,109],"it":[8],"enables":[9],"reaching":[10],"collectively":[11],"rewarding":[12],"states.":[13],"Recent":[14],"work":[15],"has":[16],"shown":[17],"that":[18,37,88],"artificial":[19],"can":[21,39],"learn":[22],"to":[23,115,121,162],"act":[24],"pro-socially":[25],"without":[26],"the":[27,119,136,152,158,174],"need":[28],"for":[29,160],"predefined":[30],"cooperative":[31],"preferences":[32],"or":[33,43],"behavioural":[34],"heuristics,":[35],"provided":[36],"they":[38],"observe":[40],"others'":[41,67],"actions":[42],"policies":[44],"and":[45,82,123,140,143,164,170],"select":[46],"them":[47],"partners":[49],"accordingly.":[50],"This":[51],"paper":[52],"relaxes":[53],"this":[54],"constraint,":[55],"studying":[56],"reinforcement":[57],"(RL)":[59],"operating":[61],"with":[62],"only":[63],"minimal":[64,101],"information":[65],"about":[66],"behaviour.":[68],"We":[69,86],"propose":[70],"a":[71],"novel":[72],"`Observer":[73],"Model',":[74],"where":[75],"gain":[77],"insights":[78],"from":[79],"direct":[80,89],"experience":[81,90],"limited,":[83],"indirect":[84],"observations.":[85],"show":[87,135],"alone":[91],"cannot":[92],"sustain":[93,124],"cooperation,":[94],"particularly":[95],"in":[96],"large":[97],"societies.":[98],"However,":[99],"even":[100],"observations":[102],"of":[103,138,176],"third-party":[104],"interactions,":[105],"allowing":[106],"few":[108],"one":[110],"observer":[111],"per":[112],"gameplay,":[113],"lead":[114],"significant":[116],"improvements,":[117],"enabling":[118],"population":[120,129],"achieve":[122],"robust":[125],"cooperation":[126,161],"across":[127],"varying":[128],"sizes.":[130],"Through":[131],"numerical":[132],"analysis,":[133],"we":[134,156,165],"co-evolution":[137],"strategy":[139],"interaction":[141],"structure":[142],"disentangle":[144],"how":[145,167],"happens":[147],"under":[148],"various":[149],"settings.":[150],"Analysing":[151],"partner":[153],"selection":[154],"graph,":[155],"identify":[157],"reasons":[159],"emerge,":[163],"explore":[166],"different":[168],"exploration":[171],"rates":[172],"affect":[173],"outcome":[175],"social":[177],"dilemmas":[178],"played":[179],"RL":[181],"agents.":[182]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}