{"id":"https://openalex.org/W2168163987","doi":"https://doi.org/10.1007/s10458-006-9007-0","title":"Exploring selfish reinforcement learning in repeated games with stochastic rewards","display_name":"Exploring selfish reinforcement learning in repeated games with stochastic rewards","publication_year":2006,"publication_date":"2006-11-09","ids":{"openalex":"https://openalex.org/W2168163987","doi":"https://doi.org/10.1007/s10458-006-9007-0","mag":"2168163987"},"language":"en","primary_location":{"id":"doi:10.1007/s10458-006-9007-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10458-006-9007-0","pdf_url":null,"source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013075653","display_name":"Katja Verbeeck","orcid":null},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Katja Verbeeck","raw_affiliation_strings":["Computational Modeling Lab (COMO), Vrije Universiteit Brussel, Brussels, Belgium"],"affiliations":[{"raw_affiliation_string":"Computational Modeling Lab (COMO), Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064553018","display_name":"Ann Now\u00e9","orcid":"https://orcid.org/0000-0001-6346-4564"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Ann Now\u00e9","raw_affiliation_strings":["Computational Modeling Lab (COMO), Vrije Universiteit Brussel, Brussels, Belgium"],"affiliations":[{"raw_affiliation_string":"Computational Modeling Lab (COMO), Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088513386","display_name":"Johan Parent","orcid":null},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Johan Parent","raw_affiliation_strings":["Computational Modeling Lab (COMO), Vrije Universiteit Brussel, Brussels, Belgium"],"affiliations":[{"raw_affiliation_string":"Computational Modeling Lab (COMO), Vrije Universiteit Brussel, Brussels, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008547992","display_name":"Karl Tuyls","orcid":"https://orcid.org/0000-0001-7929-1944"},"institutions":[{"id":"https://openalex.org/I4210105673","display_name":"Research Institute for Knowledge Systems","ror":"https://ror.org/01mzc3z63","country_code":"NL","type":"facility","lineage":["https://openalex.org/I4210105673"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Karl Tuyls","raw_affiliation_strings":["Institute for Knowledge and Agent Technology (IKAT), University of Maastricht, Maastricht, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Institute for Knowledge and Agent Technology (IKAT), University of Maastricht, Maastricht, The Netherlands","institution_ids":["https://openalex.org/I4210105673"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013075653"],"corresponding_institution_ids":["https://openalex.org/I13469542"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":6.5202,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.96510284,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"14","issue":"3","first_page":"239","last_page":"269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11031","display_name":"Game Theory and Applications","score":0.9919000267982483,"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/T11182","display_name":"Auction Theory and Applications","score":0.9684000015258789,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8537108898162842},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6851238012313843},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.6543940305709839},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6241894960403442},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6161694526672363},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.49191880226135254},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.45825186371803284},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4279490113258362},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41358956694602966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3846570551395416},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19586491584777832}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8537108898162842},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6851238012313843},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.6543940305709839},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6241894960403442},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6161694526672363},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.49191880226135254},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45825186371803284},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4279490113258362},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41358956694602966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3846570551395416},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19586491584777832},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10458-006-9007-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10458-006-9007-0","pdf_url":null,"source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},{"id":"pmh:oai:cris.maastrichtuniversity.nl:openaire_cris_publications/bc97b89d-3712-46fd-bc92-48c909d40c65","is_oa":false,"landing_page_url":"https://cris.maastrichtuniversity.nl/en/publications/bc97b89d-3712-46fd-bc92-48c909d40c65","pdf_url":null,"source":{"id":"https://openalex.org/S4306402616","display_name":"Research Publications (Maastricht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I34352273","host_organization_name":"Maastricht University","host_organization_lineage":["https://openalex.org/I34352273"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Verbeeck, K, Now\u00e9, A, Parent, J & Tuyls, K P 2007, 'Exploring Selfish Reinforcement Learning in Repeated Games with Stochastic Rewards', Autonomous Agents and Multi-agent Systems, vol. 14, no. 3, pp. 239. https://doi.org/10.1007/s10458-006-9007-0","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:40226","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/exploring-selfish-reinforcement-learning-in-repeated-games-with-stochastic-rewards(90aa8520-4c88-4515-9d42-88f4dc429f8e).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1495235237","https://openalex.org/W1515673225","https://openalex.org/W1515851193","https://openalex.org/W1519783625","https://openalex.org/W1527663244","https://openalex.org/W1538558539","https://openalex.org/W1542941925","https://openalex.org/W1546006912","https://openalex.org/W1560074431","https://openalex.org/W1569074635","https://openalex.org/W1606829969","https://openalex.org/W1626977535","https://openalex.org/W1825174002","https://openalex.org/W1826343992","https://openalex.org/W1830959208","https://openalex.org/W2067050450","https://openalex.org/W2085366587","https://openalex.org/W2104602264","https://openalex.org/W2109100253","https://openalex.org/W2112794046","https://openalex.org/W2120846115","https://openalex.org/W2121863487","https://openalex.org/W2132522159","https://openalex.org/W2138914910","https://openalex.org/W2147750403","https://openalex.org/W2164637474","https://openalex.org/W2169194711","https://openalex.org/W3121365957","https://openalex.org/W4214717370","https://openalex.org/W4247100129","https://openalex.org/W4255047891","https://openalex.org/W6631168379","https://openalex.org/W6632269551","https://openalex.org/W6677916085","https://openalex.org/W6684470913"],"related_works":["https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W2120009678","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2037601570","https://openalex.org/W2136202932","https://openalex.org/W2077555735","https://openalex.org/W3087814763"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}