{"id":"https://openalex.org/W2489939061","doi":"https://doi.org/10.1023/a:1017984413808","title":"Near-Optimal Reinforcement Learning in Polynomial Time","display_name":"Near-Optimal Reinforcement Learning in Polynomial Time","publication_year":2002,"publication_date":"2002-11-01","ids":{"openalex":"https://openalex.org/W2489939061","doi":"https://doi.org/10.1023/a:1017984413808","mag":"2489939061"},"language":"en","primary_location":{"id":"doi:10.1023/a:1017984413808","is_oa":true,"landing_page_url":"https://doi.org/10.1023/a:1017984413808","pdf_url":"https://link.springer.com/content/pdf/10.1023/A:1017984413808.pdf","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":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1023/A:1017984413808.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029730907","display_name":"Michael Kearns","orcid":"https://orcid.org/0000-0001-7569-0147"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Kearns","raw_affiliation_strings":["Department of Computer and Information Science, University of Pennsylvania, Moore School Building, 200 South 33rd Street, Philadelphia, PA, 19104-6389, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania, Moore School Building, 200 South 33rd Street, Philadelphia, PA, 19104-6389, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065366930","display_name":"Satinder Singh","orcid":"https://orcid.org/0000-0002-2736-7641"},"institutions":[{"id":"https://openalex.org/I4210107885","display_name":"Syntek Technologies (United States)","ror":"https://ror.org/01rpq5x59","country_code":"US","type":"company","lineage":["https://openalex.org/I4210107885"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satinder Singh","raw_affiliation_strings":["Syntek Capital, New York, NY, 10019, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Syntek Capital, New York, NY, 10019, USA","institution_ids":["https://openalex.org/I4210107885"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":20.4476,"has_fulltext":true,"cited_by_count":859,"citation_normalized_percentile":{"value":0.99304684,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"49","issue":"2-3","first_page":"209","last_page":"232"},"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/T12288","display_name":"Optimization and Search Problems","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9851999878883362,"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/markov-decision-process","display_name":"Markov decision process","score":0.6780298948287964},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.6421576738357544},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6058582663536072},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.559228241443634},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.5063666105270386},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5046736001968384},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.49787235260009766},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42175647616386414},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3710329234600067},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2617930769920349},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20114147663116455}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6780298948287964},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.6421576738357544},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6058582663536072},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.559228241443634},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.5063666105270386},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5046736001968384},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.49787235260009766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42175647616386414},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3710329234600067},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2617930769920349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20114147663116455},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1023/a:1017984413808","is_oa":true,"landing_page_url":"https://doi.org/10.1023/a:1017984413808","pdf_url":"https://link.springer.com/content/pdf/10.1023/A:1017984413808.pdf","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":{"id":"doi:10.1023/a:1017984413808","is_oa":true,"landing_page_url":"https://doi.org/10.1023/a:1017984413808","pdf_url":"https://link.springer.com/content/pdf/10.1023/A:1017984413808.pdf","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"},"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G8133388860","display_name":"Exploiting Structure in Reinforcement Learning Problems","funder_award_id":"9711753","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2489939061.pdf","grobid_xml":"https://content.openalex.org/works/W2489939061.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W65193931","https://openalex.org/W132264163","https://openalex.org/W1508634047","https://openalex.org/W1515851193","https://openalex.org/W1535136082","https://openalex.org/W1539216098","https://openalex.org/W1545148916","https://openalex.org/W1547105496","https://openalex.org/W1554015367","https://openalex.org/W1557517019","https://openalex.org/W1568495775","https://openalex.org/W1576452626","https://openalex.org/W1603765807","https://openalex.org/W1657674574","https://openalex.org/W1716849269","https://openalex.org/W1826343992","https://openalex.org/W1976578332","https://openalex.org/W2010343671","https://openalex.org/W2048226872","https://openalex.org/W2083143894","https://openalex.org/W2100677568","https://openalex.org/W2104335146","https://openalex.org/W2113913482","https://openalex.org/W2118219918","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2125510930","https://openalex.org/W2135630072","https://openalex.org/W2143187225","https://openalex.org/W2147750403","https://openalex.org/W2150339816","https://openalex.org/W2160067530","https://openalex.org/W2165131254","https://openalex.org/W2169982856","https://openalex.org/W2334782222","https://openalex.org/W2610841196","https://openalex.org/W2911283634","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W3139377883","https://openalex.org/W4212774754","https://openalex.org/W4214717370","https://openalex.org/W4233061323","https://openalex.org/W4233696721","https://openalex.org/W4236849587","https://openalex.org/W4245108548","https://openalex.org/W4253978526","https://openalex.org/W4298023569","https://openalex.org/W4307347247","https://openalex.org/W6602690695","https://openalex.org/W6634528131","https://openalex.org/W6677916085","https://openalex.org/W6678900246","https://openalex.org/W6780394890","https://openalex.org/W6792155000"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":28},{"year":2021,"cited_by_count":69},{"year":2020,"cited_by_count":137},{"year":2019,"cited_by_count":66},{"year":2018,"cited_by_count":51},{"year":2017,"cited_by_count":40},{"year":2016,"cited_by_count":31},{"year":2015,"cited_by_count":27},{"year":2014,"cited_by_count":31},{"year":2013,"cited_by_count":35},{"year":2012,"cited_by_count":45}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2016-08-23T00:00:00"}