{"id":"https://openalex.org/W7095583530","doi":null,"title":"efficient reinforcement learning via posterior sampling","display_name":"efficient reinforcement learning via posterior sampling","publication_year":2016,"publication_date":"2016-08-17","ids":{"openalex":"https://openalex.org/W7095583530"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.767.6458","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.767.6458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1306.0940.pdf","raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"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/A5015899120","display_name":"Ian Osband","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ian Osband","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045543562","display_name":"Benjamin Van Roy","orcid":"https://orcid.org/0000-0001-8364-3746","observed_orcids":["https://orcid.org/0000-0001-8364-3746"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin Van Roy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Daniel Russo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Russo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8773999810218811,"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":0.8773999810218811,"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":0.12210000306367874,"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":9.999999747378752e-05,"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/regret-bounds","display_name":"regret bounds","score":0.9070000052452087},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8619999885559082},{"id":"https://openalex.org/keywords/anticipated-regret","display_name":"anticipated regret","score":0.3569999933242798}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8453999757766724},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6722000241279602},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5902000069618225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.572700023651123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5604000091552734},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4941999912261963},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4690000116825104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43970000743865967},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.4293999969959259},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42329999804496765},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.40689998865127563},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3869999945163727},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3630000054836273},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.3522000014781952},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.351500004529953},{"id":"https://openalex.org/C176248197","wikidata":"https://www.wikidata.org/wiki/Q458526","display_name":"Probably approximately correct learning","level":4,"score":0.3230000138282776},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31630000472068787},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.3070000112056732},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3061999976634979},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.767.6458","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.767.6458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1306.0940.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7095823780","https://openalex.org/W2470693974","https://openalex.org/W7214740068","https://openalex.org/W4298181629","https://openalex.org/W2768473197","https://openalex.org/W3006543166","https://openalex.org/W2892024042","https://openalex.org/W4295103030","https://openalex.org/W4387161790","https://openalex.org/W4392972286"],"abstract_inverted_index":{"Most":[0],"provably-efficient":[1],"reinforcement":[2,26,148],"learning":[3,27,149],"algorithms":[4,160],"introduce":[5],"opti-mism":[6],"about":[7],"poorly-understood":[8],"states":[9],"and":[10,53,81,111,113,121,138],"actions":[11],"to":[12,85,140],"encourage":[13],"exploration.":[14],"We":[15,93,151],"study":[16],"an":[17,83,95,132],"alternative":[18],"approach":[19],"for":[20,25,68,131,146],"efficient":[21,80],"exploration:":[22],"posterior":[23],"sam-pling":[24],"(PSRL).":[28],"This":[29,124],"algorithm":[30,75,133],"proceeds":[31],"in":[32,89],"re-peated":[33],"episodes":[34],"of":[35,41,118,128,143],"known":[36],"duration.":[37],"At":[38],"the":[39,63,72,108,116,119,129,141,144],"start":[40],"each":[42],"episode,":[43],"PSRL":[44,60,156],"updates":[45],"a":[46,90],"prior":[47,87],"distribution":[48],"over":[49],"Markov":[50],"decision":[51],"processes":[52],"takes":[54],"one":[55,127],"sample":[56,70],"from":[57],"this":[58,69],"posterior.":[59],"then":[61],"follows":[62],"policy":[64],"that":[65,155],"is":[66,76,104,107,126],"optimal":[67],"during":[71],"episode.":[73],"The":[74],"conceptually":[77],"simple,":[78],"computationally":[79],"allows":[82],"agent":[84],"encode":[86],"knowledge":[88],"natural":[91],"way.":[92],"establish":[94],"O\u0303(\u03c4S":[96],"AT)":[97],"bound":[98,125],"on":[99,136],"expected":[100],"regret,":[101],"where":[102],"T":[103],"time,":[105],"\u03c4":[106],"episode":[109],"length":[110],"S":[112],"A":[114],"are":[115],"cardinali-ties":[117],"state":[120,142],"action":[122],"spaces.":[123],"first":[130],"not":[134],"based":[135],"optimism,":[137],"close":[139],"art":[145],"any":[147],"algorithm.":[150],"show":[152],"through":[153],"simulation":[154],"significantly":[157],"outperforms":[158],"existing":[159],"with":[161],"similar":[162],"regret":[163],"bounds.":[164],"1":[165]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-27T00:00:00"}