{"id":"https://openalex.org/W1931027396","doi":null,"title":"High Confidence Policy Improvement","display_name":"High Confidence Policy Improvement","publication_year":2015,"publication_date":"2015-07-06","ids":{"openalex":"https://openalex.org/W1931027396","mag":"1931027396"},"language":"en","primary_location":{"id":"mag:1931027396","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v37/thomas15.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null},"volume":null,"type":"conference-paper","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/A5066332280","display_name":"Philip S. Thomas","orcid":"https://orcid.org/0000-0002-9904-1800","observed_orcids":["https://orcid.org/0000-0002-9904-1800"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip S. Thomas","raw_affiliation_strings":["University of Massachusetts: Amherst#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-9904-1800","affiliations":[{"raw_affiliation_string":"University of Massachusetts: Amherst#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066303412","display_name":"Georgios Theocharous","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Georgios Theocharous","raw_affiliation_strings":["Adobe Research,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research,,,,,","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013843778","display_name":"Mohammad Ghavamzadeh","orcid":"https://orcid.org/0000-0003-0930-8688","observed_orcids":["https://orcid.org/0000-0003-0930-8688"]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Ghavamzadeh","raw_affiliation_strings":["Adobe Research,,,,,"],"raw_orcid":"https://orcid.org/0000-0003-0930-8688","affiliations":[{"raw_affiliation_string":"Adobe Research,,,,,","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3031,"has_fulltext":false,"cited_by_count":107,"citation_normalized_percentile":{"value":0.95929561,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2380","last_page":"2388"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.0005000000237487257,"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/policy-improvement","display_name":"policy improvement","score":0.7580000162124634},{"id":"https://openalex.org/keywords/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":0.9670000076293945},{"id":"https://openalex.org/keywords/probabilistic-guarantees","display_name":"probabilistic guarantees","score":0.9200000166893005},{"id":"https://openalex.org/keywords/confidence-limits","display_name":"confidence limits","score":0.7200000286102295},{"id":"https://openalex.org/keywords/performance-lower-bound","display_name":"performance lower bound","score":0.652999997138977},{"id":"https://openalex.org/keywords/mountain-car-problem","display_name":"mountain car problem","score":0.8289999961853027},{"id":"https://openalex.org/keywords/digital-marketing","display_name":"digital marketing","score":0.7749999761581421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773603081703186},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7617976665496826},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7198798656463623},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4693528115749359},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46443209052085876},{"id":"https://openalex.org/C128669082","wikidata":"https://www.wikidata.org/wiki/Q583461","display_name":"Randomized algorithm","level":2,"score":0.45548927783966064},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.422041654586792},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3705672025680542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35635197162628174},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3242705166339874},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2922002673149109},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10130864381790161},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:1931027396","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v37/thomas15.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W102487131","https://openalex.org/W107583932","https://openalex.org/W1514587017","https://openalex.org/W1515851193","https://openalex.org/W1575592356","https://openalex.org/W1995945562","https://openalex.org/W2047038914","https://openalex.org/W2097879961","https://openalex.org/W2098184356","https://openalex.org/W2099833070","https://openalex.org/W2106261932","https://openalex.org/W2107726111","https://openalex.org/W2110065044","https://openalex.org/W2112583795","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2122124659","https://openalex.org/W2126728600","https://openalex.org/W2155982020","https://openalex.org/W2229272015","https://openalex.org/W2273088453"],"related_works":["https://openalex.org/W3178284873","https://openalex.org/W2963208223","https://openalex.org/W4393156271","https://openalex.org/W7216480551","https://openalex.org/W2958919132","https://openalex.org/W2780045768","https://openalex.org/W2966270442","https://openalex.org/W2963044034","https://openalex.org/W3035367521","https://openalex.org/W4298008065"],"abstract_inverted_index":{"We":[0,63,81],"present":[1],"a":[2,53,89,102],"batch":[3],"reinforcement":[4],"learning":[5],"(RL)":[6],"algorithm":[7,44,68,74],"that":[8,18,26,47,50,69,106],"provides":[9],"probabilistic":[10],"guarantees":[11],"about":[12],"the":[13,48,83,93],"quality":[14],"of":[15,85],"each":[16],"policy":[17,54,72,79],"it":[19,51],"proposes,":[20],"and":[21,38,42,92],"which":[22],"has":[23],"no":[24],"hyper-parameters":[25],"require":[27],"expert":[28],"tuning.":[29],"The":[30],"user":[31],"may":[32],"select":[33],"any":[34],"performance":[35,56],"lower-bound,":[36],"\u03c1-,":[37],"confidence":[39],"level,":[40],"\u03b4,":[41],"our":[43,71,86],"will":[45],"ensure":[46],"probability":[49],"returns":[52],"with":[55,88,101],"below":[57],"\u03c1-":[58],"is":[59],"at":[60],"most":[61],"\u03b4.":[62],"then":[64],"propose":[65],"an":[66],"incremental":[67],"executes":[70],"improvement":[73],"repeatedly":[75],"to":[76],"generate":[77],"multiple":[78],"improvements.":[80],"show":[82],"viability":[84],"approach":[87],"simple":[90],"gridworld":[91],"standard":[94],"mountain":[95],"car":[96],"problem,":[97],"as":[98,100],"well":[99],"digital":[103],"marketing":[104],"application":[105],"uses":[107],"real":[108],"world":[109],"data.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}