{"id":"https://openalex.org/W1963523946","doi":"https://doi.org/10.1007/s10994-010-5192-9","title":"Learning to compete, coordinate, and cooperate in\u00a0repeated games using reinforcement learning","display_name":"Learning to compete, coordinate, and cooperate in\u00a0repeated games using reinforcement learning","publication_year":2010,"publication_date":"2010-05-19","ids":{"openalex":"https://openalex.org/W1963523946","doi":"https://doi.org/10.1007/s10994-010-5192-9","mag":"1963523946"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-010-5192-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10994-010-5192-9","pdf_url":null,"source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","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/A5059420501","display_name":"Jacob W. Crandall","orcid":"https://orcid.org/0000-0002-5602-4146"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jacob W. Crandall","raw_affiliation_strings":["Computing and Information Science Program, Masdar Institute of Science and Technology, Abu Dhabi, UAE","Computing and Information Science Program, Masdar Institute of Science and Technology, Abu Dhabi, UAE#TAB#"],"affiliations":[{"raw_affiliation_string":"Computing and Information Science Program, Masdar Institute of Science and Technology, Abu Dhabi, UAE","institution_ids":[]},{"raw_affiliation_string":"Computing and Information Science Program, Masdar Institute of Science and Technology, Abu Dhabi, UAE#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077345598","display_name":"Michael A. Goodrich","orcid":"https://orcid.org/0000-0002-2489-5705"},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael A. Goodrich","raw_affiliation_strings":["Computer Science Department, Brigham Young University, Provo, UT, USA","Computer Science Department, Brigham Young University, Provo, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Brigham Young University, Provo, UT, USA","institution_ids":["https://openalex.org/I100005738"]},{"raw_affiliation_string":"Computer Science Department, Brigham Young University, Provo, USA#TAB#","institution_ids":["https://openalex.org/I100005738"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059420501"],"corresponding_institution_ids":[],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":5.1609,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.95092162,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"82","issue":"3","first_page":"281","last_page":"314"},"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":0.9991000294685364,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9970999956130981,"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":0.7593643069267273},{"id":"https://openalex.org/keywords/repeated-game","display_name":"Repeated game","score":0.6784249544143677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6265888810157776},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5834290981292725},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.5004017353057861},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.47651994228363037},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4256082773208618},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.42530357837677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4160202741622925},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3635965883731842},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.3364470899105072},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.29804226756095886},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25904563069343567},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22644585371017456}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7593643069267273},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.6784249544143677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6265888810157776},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5834290981292725},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.5004017353057861},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.47651994228363037},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4256082773208618},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.42530357837677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4160202741622925},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3635965883731842},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3364470899105072},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.29804226756095886},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25904563069343567},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22644585371017456}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-010-5192-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10994-010-5192-9","pdf_url":null,"source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W28155157","https://openalex.org/W82142180","https://openalex.org/W137071854","https://openalex.org/W789315506","https://openalex.org/W1495235237","https://openalex.org/W1505937442","https://openalex.org/W1513468570","https://openalex.org/W1515108343","https://openalex.org/W1519783625","https://openalex.org/W1542941925","https://openalex.org/W1557517019","https://openalex.org/W1575244154","https://openalex.org/W1605188341","https://openalex.org/W1656616331","https://openalex.org/W1988790447","https://openalex.org/W1990870166","https://openalex.org/W2012661833","https://openalex.org/W2017990047","https://openalex.org/W2028798910","https://openalex.org/W2043989834","https://openalex.org/W2053616263","https://openalex.org/W2062663664","https://openalex.org/W2065096320","https://openalex.org/W2087322096","https://openalex.org/W2097498347","https://openalex.org/W2103437045","https://openalex.org/W2105507006","https://openalex.org/W2105643086","https://openalex.org/W2107726111","https://openalex.org/W2112223472","https://openalex.org/W2112794046","https://openalex.org/W2116067849","https://openalex.org/W2118994458","https://openalex.org/W2120327309","https://openalex.org/W2121180068","https://openalex.org/W2121863487","https://openalex.org/W2123085572","https://openalex.org/W2124951424","https://openalex.org/W2125631327","https://openalex.org/W2133096155","https://openalex.org/W2135730283","https://openalex.org/W2138362680","https://openalex.org/W2145067550","https://openalex.org/W2148825261","https://openalex.org/W2150039384","https://openalex.org/W2156194062","https://openalex.org/W2164637474","https://openalex.org/W2575731723","https://openalex.org/W2595697910","https://openalex.org/W2612972698","https://openalex.org/W2951054971","https://openalex.org/W2999905431","https://openalex.org/W3105048218","https://openalex.org/W3122023814","https://openalex.org/W3143250040","https://openalex.org/W4211108372","https://openalex.org/W4214717370","https://openalex.org/W4241387086","https://openalex.org/W4243845907","https://openalex.org/W4248437541","https://openalex.org/W4251841679","https://openalex.org/W4285719527","https://openalex.org/W6601295022","https://openalex.org/W6603358185","https://openalex.org/W6608726207","https://openalex.org/W6631168379","https://openalex.org/W6634562073","https://openalex.org/W6635846226","https://openalex.org/W6661695161","https://openalex.org/W6665817581","https://openalex.org/W6677916085","https://openalex.org/W6680197816","https://openalex.org/W6684470913","https://openalex.org/W7038818850"],"related_works":["https://openalex.org/W2016058626","https://openalex.org/W2735052328","https://openalex.org/W3125137934","https://openalex.org/W1528395754","https://openalex.org/W2101010482","https://openalex.org/W2371469815","https://openalex.org/W4230011720","https://openalex.org/W2122010238","https://openalex.org/W4301668927","https://openalex.org/W4288917516"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}