{"id":"https://openalex.org/W2124352385","doi":"https://doi.org/10.1145/1553374.1553441","title":"Near-Bayesian exploration in polynomial time","display_name":"Near-Bayesian exploration in polynomial time","publication_year":2009,"publication_date":"2009-06-14","ids":{"openalex":"https://openalex.org/W2124352385","doi":"https://doi.org/10.1145/1553374.1553441","mag":"2124352385"},"language":"en","primary_location":{"id":"doi:10.1145/1553374.1553441","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","raw_type":"proceedings-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/A5075035644","display_name":"J. Zico Kolter","orcid":"https://orcid.org/0000-0002-8106-5759"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"J. Zico Kolter","raw_affiliation_strings":["Stanford University, CA"],"affiliations":[{"raw_affiliation_string":"Stanford University, CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112456378","display_name":"Andrew Y. Ng","orcid":"https://orcid.org/0000-0001-5547-3196"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Y. Ng","raw_affiliation_strings":["Stanford University, CA"],"affiliations":[{"raw_affiliation_string":"Stanford University, CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075035644"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":21.6244,"has_fulltext":false,"cited_by_count":238,"citation_normalized_percentile":{"value":0.99524246,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"513","last_page":"520"},"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9980999827384949,"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":0.9979000091552734,"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/bayesian-probability","display_name":"Bayesian probability","score":0.729482889175415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6784805059432983},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6643176674842834},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.5997076630592346},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.5576352477073669},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5075374841690063},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.49683716893196106},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.42163345217704773},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.4199601411819458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39325782656669617},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3896651566028595},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2633005380630493}],"concepts":[{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.729482889175415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6784805059432983},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6643176674842834},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.5997076630592346},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.5576352477073669},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5075374841690063},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.49683716893196106},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.42163345217704773},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.4199601411819458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39325782656669617},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3896651566028595},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2633005380630493},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1553374.1553441","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6664096962","display_name":null,"funder_award_id":"FA8650-05-C-7261","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W107583932","https://openalex.org/W1496855202","https://openalex.org/W1505937442","https://openalex.org/W1525953815","https://openalex.org/W1554015367","https://openalex.org/W1582436621","https://openalex.org/W1747856733","https://openalex.org/W1952404018","https://openalex.org/W1988526405","https://openalex.org/W2005306124","https://openalex.org/W2071814471","https://openalex.org/W2097931172","https://openalex.org/W2116459397","https://openalex.org/W2119567691","https://openalex.org/W2124352385","https://openalex.org/W2125710232","https://openalex.org/W2129670787","https://openalex.org/W2134807560","https://openalex.org/W2485373351","https://openalex.org/W2489939061","https://openalex.org/W4254113915","https://openalex.org/W4285719527","https://openalex.org/W4298023569","https://openalex.org/W6629614444","https://openalex.org/W6634907821","https://openalex.org/W6637888334","https://openalex.org/W6724046077"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2877093712","https://openalex.org/W2116157560","https://openalex.org/W4310614650","https://openalex.org/W1774334694"],"abstract_inverted_index":{"We":[0],"consider":[1],"the":[2,36,68,81,94,103,134],"exploration/exploitation":[3],"problem":[4],"in":[5,78],"reinforcement":[6],"learning":[7],"(RL).":[8],"The":[9,87],"Bayesian":[10,37,72,106],"approach":[11],"to":[12,19,31,64,67],"model-based":[13],"RL":[14],"offers":[15],"an":[16,126],"elegant":[17],"solution":[18,38],"this":[20,48,109],"problem,":[21],"by":[22,93],"considering":[23],"a":[24,52],"distribution":[25],"over":[26],"possible":[27],"models":[28],"and":[29,55,89,98],"acting":[30],"maximize":[32],"expected":[33],"reward;":[34],"unfortunately,":[35],"is":[39,62,130],"intractable":[40],"for":[41],"all":[42],"but":[43],"very":[44],"restricted":[45],"cases.":[46],"In":[47,108],"paper":[49],"we":[50,111,114],"present":[51],"simple":[53],"algorithm,":[54],"prove":[56],"that":[57,113,129],"with":[58],"high":[59],"probability":[60],"it":[61],"able":[63],"perform":[65],"\u03b5-close":[66],"true":[69],"(intractable)":[70],"optimal":[71],"policy":[73],"after":[74],"some":[75],"small":[76],"(polynomial":[77],"quantities":[79],"describing":[80],"system)":[82],"number":[83],"of":[84,105,138],"time":[85],"steps.":[86],"algorithm":[88],"analysis":[90],"are":[91],"motivated":[92],"so-called":[95],"PAC-MDP":[96,139],"approach,":[97],"extend":[99],"such":[100],"results":[101],"into":[102],"setting":[104],"RL.":[107],"setting,":[110],"show":[112],"can":[115],"achieve":[116],"lower":[117],"sample":[118],"complexity":[119],"bounds":[120],"than":[121,133],"existing":[122],"algorithms,":[123],"while":[124],"using":[125],"exploration":[127,137],"strategy":[128],"much":[131],"greedier":[132],"(extremely":[135],"cautious)":[136],"algorithms.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":18},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":25},{"year":2012,"cited_by_count":25}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}