{"id":"https://openalex.org/W1496720559","doi":null,"title":"Optimistic linear programming gives logarithmic regret for irreducible MDPs","display_name":"Optimistic linear programming gives logarithmic regret for irreducible MDPs","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W1496720559","mag":"1496720559"},"language":"en","primary_location":{"id":"pmh:oai:eprints.qut.edu.au:45645","doi":null,"is_oa":false,"landing_page_url":"http://books.nips.cc/papers/files/nips20/NIPS2007_0673.pdf","pdf_url":"http://books.nips.cc/papers/files/nips20/NIPS2007_0673.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Advances in Neural Information Processing Systems 20: Proceedings of the 2007 Conference","raw_type":"Chapter in Book, Report or Conference volume"},"volume":null,"type":"conference-paper","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/A5051918150","display_name":"Ambuj Tewari","orcid":"https://orcid.org/0000-0001-6969-7844","observed_orcids":["https://orcid.org/0000-0001-6969-7844"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ambuj Tewari","raw_affiliation_strings":["Computer Science Division, Univeristy of California, Berkeley, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Division, Univeristy of California, Berkeley, CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030261391","display_name":"Peter L. Bartlett","orcid":"https://orcid.org/0000-0002-8760-3140","observed_orcids":["https://orcid.org/0000-0002-8760-3140"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter L. Bartlett","raw_affiliation_strings":["Computer Science Division and Department of Statistics, University of California, Berkeley, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Division and Department of Statistics, University of California, Berkeley, CA#TAB#","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":4.4319,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.94264544,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9868000149726868,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9868000149726868,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.012500000186264515,"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":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/markov-decision-process","display_name":"Markov decision process","score":0.9549999833106995},{"id":"https://openalex.org/keywords/average-reward","display_name":"average reward","score":0.6349999904632568},{"id":"https://openalex.org/keywords/regret-bounds","display_name":"regret bounds","score":0.9129999876022339},{"id":"https://openalex.org/keywords/linear-programming","display_name":"linear programming","score":0.6890000104904175},{"id":"https://openalex.org/keywords/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.5839999914169312},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.36800000071525574},{"id":"https://openalex.org/keywords/unknown-transition-probabilities","display_name":"unknown transition probabilities","score":0.5170000195503235}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9620171189308167},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6967868804931641},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.6503958702087402},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.5356326699256897},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.5252677798271179},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.49054139852523804},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4862005114555359},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4408721625804901},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43209218978881836},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42664164304733276},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3909403383731842},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.33094972372055054},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24562889337539673},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1284470558166504},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:eprints.qut.edu.au:45645","doi":null,"is_oa":false,"landing_page_url":"http://books.nips.cc/papers/files/nips20/NIPS2007_0673.pdf","pdf_url":"http://books.nips.cc/papers/files/nips20/NIPS2007_0673.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Advances in Neural Information Processing Systems 20: Proceedings of the 2007 Conference","raw_type":"Chapter in Book, Report or Conference volume"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.69.5482","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.69.5482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://books.nips.cc/papers/files/nips20/NIPS2007_0673.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.70.9796","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.70.9796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://books.nips.cc/papers/files/nips20/NIPS2007_0673.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.84.8622","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.84.8622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~ambuj/research/tewari08optimistic.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391020686","https://openalex.org/W4321012151","https://openalex.org/W4318719340","https://openalex.org/W4287326952","https://openalex.org/W4387800195","https://openalex.org/W3020125231","https://openalex.org/W3045472490","https://openalex.org/W2951640715","https://openalex.org/W3131233483","https://openalex.org/W4376654472"],"abstract_inverted_index":{"We":[0,65],"present":[1],"an":[2,16,95,104,159],"algorithm":[3,105,160],"called":[4],"Optimistic":[5],"Linear":[6],"Programming":[7],"(OLP)":[8],"for":[9],"learning":[10],"to":[11,31,54,61,76,103,158],"optimize":[12],"average":[13],"reward":[14,71,86],"in":[15,156],"irreducible":[17],"but":[18,137],"otherwise":[19],"unknown":[20],"Markov":[21],"decision":[22],"process":[23],"(MDP).":[24],"OLP":[25,74,99,115,152,168],"uses":[26],"its":[27,172],"experience":[28],"so":[29],"far":[30],"estimate":[32],"the":[33,55,68,85,89,124,129,132,147,180,183],"MDP.":[34,184],"It":[35],"chooses":[36],"actions":[37],"by":[38,73,88,107,163],"optimistically":[39],"maximizing":[40],"estimated":[41],"future":[42],"rewards":[43],"over":[44],"a":[45,57,142,176],"set":[46],"of":[47,84,123,126,131,149,182],"next-state":[48],"transition":[49,127],"probabilities":[50],"that":[51,59,67],"are":[52],"close":[53],"estimates,":[56],"computation":[58],"corresponds":[60],"solving":[62],"linear":[63],"programs.":[64],"show":[66],"total":[69],"expected":[70],"obtained":[72,87],"up":[75],"time":[77],"T":[78,83],"is":[79,94,100,116,135,141,153,169],"within":[80],"C(P)":[81,93],"log":[82],"optimal":[90],"policy,":[91],"where":[92],"explicit,":[96],"MDP-dependent":[97],"constant.":[98],"closely":[101],"related":[102],"proposed":[106,162],"Burnetas":[108],"and":[109,165,171],"Katehakis":[110],"with":[111],"four":[112],"key":[113],"differences:":[114],"simpler,":[117,136],"it":[118],"does":[119],"not":[120],"require":[121],"knowledge":[122],"supports":[125],"probabilities,":[128],"proof":[130],"regret":[133,139,148,173],"bound":[134,140,174],"our":[138],"constant":[143],"factor":[144],"larger":[145],"than":[146],"their":[150],"algorithm.":[151],"also":[154],"similar":[155],"flavor":[157],"recently":[161],"Auer":[164],"Ortner.":[166],"But":[167],"simpler":[170],"has":[175],"better":[177],"dependence":[178],"on":[179],"size":[181],"1":[185]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}