{"id":"https://openalex.org/W2129670787","doi":"https://doi.org/10.1145/1143844.1143955","title":"PAC model-free reinforcement learning","display_name":"PAC model-free reinforcement learning","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2129670787","doi":"https://doi.org/10.1145/1143844.1143955","mag":"2129670787"},"language":"en","primary_location":{"id":"doi:10.1145/1143844.1143955","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1143844.1143955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Machine learning - ICML '06","raw_type":"proceedings-article"},"type":"conference-paper","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/A5085896252","display_name":"Alexander L. Strehl","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander L. Strehl","raw_affiliation_strings":["Rutgers University, Piscataway, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100711454","display_name":"Lihong Li","orcid":"https://orcid.org/0000-0002-5440-8242"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lihong Li","raw_affiliation_strings":["Rutgers University, Piscataway, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085248782","display_name":"Eric Wiewiora","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Wiewiora","raw_affiliation_strings":["University of California, San Diego","University of California,  San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"University of California,  San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005003250","display_name":"John Langford","orcid":"https://orcid.org/0000-0002-9811-3550"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Langford","raw_affiliation_strings":["TTI-Chicago, Chicago, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TTI-Chicago, Chicago, IL","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009722403","display_name":"Michael L. Littman","orcid":"https://orcid.org/0000-0002-5596-1840"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Littman","raw_affiliation_strings":["Rutgers University, Piscataway, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6183,"has_fulltext":false,"cited_by_count":415,"citation_normalized_percentile":{"value":0.96947487,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"881","last_page":"888"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9879000186920166,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9829000234603882,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8747074007987976},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8505856990814209},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7472025752067566},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7127528190612793},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6153542399406433},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5716570615768433},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5155277252197266},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4940198063850403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4219844341278076},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.41356271505355835},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3494085371494293},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32826757431030273},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.31624656915664673},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13986966013908386},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07818496227264404}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8747074007987976},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8505856990814209},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7472025752067566},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7127528190612793},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6153542399406433},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5716570615768433},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5155277252197266},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4940198063850403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4219844341278076},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.41356271505355835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3494085371494293},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32826757431030273},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31624656915664673},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13986966013908386},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07818496227264404},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1143844.1143955","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1143844.1143955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Machine learning - ICML '06","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.120.326","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.120.326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.tufts.edu/~roni/Teaching/RL/Papers/ICML06PACModelFreeRLLong.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.137.4712","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.137.4712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hunch.net/~jl/projects/RL/Delayed_Q/icml06.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.966","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.966","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://imls.engr.oregonstate.edu/www/htdocs/proceedings/icml2006/111_PAC_Model_free_Reinf.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.75,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W107583932","https://openalex.org/W1515851193","https://openalex.org/W2009533501","https://openalex.org/W2082691056","https://openalex.org/W2083143894","https://openalex.org/W2118686230","https://openalex.org/W2121863487","https://openalex.org/W2122701159","https://openalex.org/W2489939061","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2357975469","https://openalex.org/W2101748387","https://openalex.org/W3096874164","https://openalex.org/W2807018115","https://openalex.org/W4388236136","https://openalex.org/W4281812492","https://openalex.org/W2315999538","https://openalex.org/W3105579180","https://openalex.org/W4200250224"],"abstract_inverted_index":{"For":[0],"a":[1,19,59,70],"Markov":[2],"Decision":[3],"Process":[4],"with":[5],"finite":[6],"state":[7],"(size":[8,13],"S)":[9],"and":[10,86],"action":[11],"spaces":[12],"A":[14],"per":[15],"state),":[16],"we":[17],"propose":[18],"new":[20],"algorithm---Delayed":[21],"Q-Learning.":[22],"We":[23],"prove":[24],"it":[25],"is":[26,55,80,94],"PAC,":[27],"achieving":[28],"near":[29],"optimal":[30],"performance":[31],"except":[32],"for":[33],"\u00d5(SA)":[34],"timesteps":[35],"using":[36],"O(SA)":[37],"space,":[38],"improving":[39],"on":[40],"the":[41,62],"\u00d5(S2":[42],"A)":[43],"bounds":[44],"of":[45,61,74,99],"best":[46],"previous":[47,100],"algorithms.":[48,102],"This":[49],"result":[50],"proves":[51],"efficient":[52],"reinforcement":[53],"learning":[54,58],"possible":[56],"without":[57],"model":[60],"MDP":[63],"from":[64,69],"experience.":[65],"Learning":[66],"takes":[67],"place":[68],"single":[71],"continuous":[72],"thread":[73],"experience---no":[75],"resets":[76],"nor":[77],"parallel":[78],"sampling":[79],"used.":[81],"Beyond":[82],"its":[83],"smaller":[84],"storage":[85],"experience":[87],"requirements,":[88],"Delayed":[89],"Q-learning's":[90],"per-experience":[91],"computation":[92],"cost":[93],"much":[95],"less":[96],"than":[97],"that":[98],"PAC":[101]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":31},{"year":2021,"cited_by_count":45},{"year":2020,"cited_by_count":58},{"year":2019,"cited_by_count":42},{"year":2018,"cited_by_count":33},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":20},{"year":2013,"cited_by_count":22},{"year":2012,"cited_by_count":16}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}