{"id":"https://openalex.org/W1973039793","doi":"https://doi.org/10.1016/s1389-0417(01)00015-8","title":"Value-function reinforcement learning in Markov games","display_name":"Value-function reinforcement learning in Markov games","publication_year":2001,"publication_date":"2001-04-01","ids":{"openalex":"https://openalex.org/W1973039793","doi":"https://doi.org/10.1016/s1389-0417(01)00015-8","mag":"1973039793"},"language":"en","primary_location":{"id":"doi:10.1016/s1389-0417(01)00015-8","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s1389-0417(01)00015-8","pdf_url":null,"source":{"id":"https://openalex.org/S96254641","display_name":"Cognitive Systems Research","issn_l":"1389-0417","issn":["1389-0417","2214-4366"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Systems Research","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/A5009722403","display_name":"Michael L. Littman","orcid":"https://orcid.org/0000-0002-5596-1840"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Michael L. Littman","raw_affiliation_strings":["AT&T Labs Research, 180 Park Avenue, Florham Park, NJ 07932-0971, USA","AT&T Labs \u2013\u2013 Research, 180 Park Avenue, Florham Park, NJ 07932-0971, USA"],"affiliations":[{"raw_affiliation_string":"AT&T Labs Research, 180 Park Avenue, Florham Park, NJ 07932-0971, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Labs \u2013\u2013 Research, 180 Park Avenue, Florham Park, NJ 07932-0971, USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5009722403"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":{"value":2770,"currency":"USD","value_usd":2770},"apc_paid":null,"fwci":8.1768,"has_fulltext":false,"cited_by_count":409,"citation_normalized_percentile":{"value":0.97112402,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"2","issue":"1","first_page":"55","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9966999888420105,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8774411678314209},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7708299160003662},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6965512633323669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6760666370391846},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.6154934763908386},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6131134629249573},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5606254935264587},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5516756176948547},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5355783104896545},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5017228126525879},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.48136669397354126},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4517658054828644},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4434865117073059},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41528111696243286},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.26581573486328125},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19419512152671814},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06763949990272522},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05260077118873596}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8774411678314209},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7708299160003662},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6965512633323669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6760666370391846},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6154934763908386},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6131134629249573},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5606254935264587},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5516756176948547},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5355783104896545},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5017228126525879},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.48136669397354126},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4517658054828644},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4434865117073059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41528111696243286},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26581573486328125},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19419512152671814},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06763949990272522},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05260077118873596},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/s1389-0417(01)00015-8","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s1389-0417(01)00015-8","pdf_url":null,"source":{"id":"https://openalex.org/S96254641","display_name":"Cognitive Systems Research","issn_l":"1389-0417","issn":["1389-0417","2214-4366"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cognitive Systems Research","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.217.7294","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.217.7294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cogsci.rpi.edu/~rsun/si-mal/article3.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W58712762","https://openalex.org/W276645413","https://openalex.org/W354832773","https://openalex.org/W1496590343","https://openalex.org/W1513468570","https://openalex.org/W1515108343","https://openalex.org/W1521003796","https://openalex.org/W1542941925","https://openalex.org/W1545148916","https://openalex.org/W1548536111","https://openalex.org/W1560420247","https://openalex.org/W1573854133","https://openalex.org/W1610678877","https://openalex.org/W1626977535","https://openalex.org/W1835254890","https://openalex.org/W2028145673","https://openalex.org/W2041660482","https://openalex.org/W2060587510","https://openalex.org/W2080631849","https://openalex.org/W2089415692","https://openalex.org/W2100677568","https://openalex.org/W2104602264","https://openalex.org/W2107726111","https://openalex.org/W2119567691","https://openalex.org/W2142839172","https://openalex.org/W2144846366","https://openalex.org/W2147750403","https://openalex.org/W2150339816","https://openalex.org/W2159206500","https://openalex.org/W2159934831","https://openalex.org/W2165131254","https://openalex.org/W2334782222","https://openalex.org/W2575731723","https://openalex.org/W2603873353","https://openalex.org/W2912485311","https://openalex.org/W2914933231","https://openalex.org/W3011120880","https://openalex.org/W3027820740","https://openalex.org/W3041202696","https://openalex.org/W4214717370","https://openalex.org/W4233696721","https://openalex.org/W4241706417","https://openalex.org/W6630520071","https://openalex.org/W6630838994","https://openalex.org/W6631137000","https://openalex.org/W6632558091","https://openalex.org/W6632678946","https://openalex.org/W6634421576","https://openalex.org/W6636530465","https://openalex.org/W6636868823","https://openalex.org/W6638624986","https://openalex.org/W6675811377","https://openalex.org/W6681246212","https://openalex.org/W6683643218"],"related_works":["https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W3096874164","https://openalex.org/W2357975469","https://openalex.org/W2937181779","https://openalex.org/W2808418668","https://openalex.org/W2025663273","https://openalex.org/W2145363145","https://openalex.org/W3168977894","https://openalex.org/W1574958246"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":29},{"year":2022,"cited_by_count":29},{"year":2021,"cited_by_count":35},{"year":2020,"cited_by_count":47},{"year":2019,"cited_by_count":32},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":21},{"year":2013,"cited_by_count":18},{"year":2012,"cited_by_count":12}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}