{"id":"https://openalex.org/W2014320009","doi":"https://doi.org/10.1109/cdc.2010.5717930","title":"Q-learning and enhanced policy iteration in discounted dynamic programming","display_name":"Q-learning and enhanced policy iteration in discounted dynamic programming","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2014320009","doi":"https://doi.org/10.1109/cdc.2010.5717930","mag":"2014320009"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2010.5717930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2010.5717930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"49th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1721.1/121248","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039911471","display_name":"Dimitri P. Bertsekas","orcid":"https://orcid.org/0000-0001-6909-7208"},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dimitri P. Bertsekas","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, MIT, Cambridge, MA, USA","Dept. of Electr. Engineering and Comp. Science, M.I.T., Cambridge, Mass., 02139, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210110987"]},{"raw_affiliation_string":"Dept. of Electr. Engineering and Comp. Science, M.I.T., Cambridge, Mass., 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014937312","display_name":"Huizhen Yu","orcid":"https://orcid.org/0000-0002-3673-0094"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Huizhen Yu","raw_affiliation_strings":["Department of Computer Science, University of Helsinki, Finland","Department of Computer Science, University of Helsinki, Finland,"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]},{"raw_affiliation_string":"Department of Computer Science, University of Helsinki, Finland,","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039911471"],"corresponding_institution_ids":["https://openalex.org/I4210110987","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":4.6549,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.94579603,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"3","issue":null,"first_page":"1409","last_page":"1416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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":0.9983000159263611,"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/T12288","display_name":"Optimization and Search Problems","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T13553","display_name":"Age of Information Optimization","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7061637043952942},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6022655963897705},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5798272490501404},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5511736273765564},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5454067587852478},{"id":"https://openalex.org/keywords/lookup-table","display_name":"Lookup table","score":0.5219835042953491},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5191713571548462},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49429750442504883},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4681772291660309},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.456143856048584},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4480118751525879},{"id":"https://openalex.org/keywords/optimal-stopping","display_name":"Optimal stopping","score":0.44700998067855835},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.4241468906402588},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4151463806629181},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.40098345279693604},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.36070430278778076},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3164918124675751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14431893825531006}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7061637043952942},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6022655963897705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5798272490501404},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5511736273765564},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5454067587852478},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.5219835042953491},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5191713571548462},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49429750442504883},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4681772291660309},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.456143856048584},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4480118751525879},{"id":"https://openalex.org/C99414536","wikidata":"https://www.wikidata.org/wiki/Q7098950","display_name":"Optimal stopping","level":2,"score":0.44700998067855835},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.4241468906402588},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4151463806629181},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.40098345279693604},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.36070430278778076},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3164918124675751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14431893825531006},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/cdc.2010.5717930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2010.5717930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"49th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.8483","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.8483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.mit.edu/dimitrib/www/Enhanced_Policy_Iteration.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.421.283","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.421.283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://stuff.mit.edu/people/dimitrib/Enhanced_Policy_Iteration.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/121248","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/121248","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"http://purl.org/eprint/type/JournalArticle"},{"id":"pmh:oai:helda.helsinki.fi:10138/17117","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/17117","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Technical report"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/121248","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/121248","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MIT web domain","raw_type":"http://purl.org/eprint/type/JournalArticle"},"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W359568995","https://openalex.org/W565357261","https://openalex.org/W594357522","https://openalex.org/W1534175858","https://openalex.org/W1547105496","https://openalex.org/W1576452626","https://openalex.org/W1600046456","https://openalex.org/W1601081659","https://openalex.org/W1603765807","https://openalex.org/W1626155273","https://openalex.org/W1984669689","https://openalex.org/W1998172110","https://openalex.org/W2014320009","https://openalex.org/W2019172585","https://openalex.org/W2021247827","https://openalex.org/W2027855416","https://openalex.org/W2028145673","https://openalex.org/W2062541405","https://openalex.org/W2072931156","https://openalex.org/W2075268401","https://openalex.org/W2080631849","https://openalex.org/W2084202551","https://openalex.org/W2098432798","https://openalex.org/W2100677568","https://openalex.org/W2100857832","https://openalex.org/W2104335146","https://openalex.org/W2106647675","https://openalex.org/W2118458590","https://openalex.org/W2119380668","https://openalex.org/W2119567691","https://openalex.org/W2122945138","https://openalex.org/W2124477018","https://openalex.org/W2132351269","https://openalex.org/W2134042548","https://openalex.org/W2141022000","https://openalex.org/W2147750403","https://openalex.org/W2147839652","https://openalex.org/W2150123286","https://openalex.org/W2153267861","https://openalex.org/W2154761920","https://openalex.org/W2154834860","https://openalex.org/W2155143729","https://openalex.org/W2156168464","https://openalex.org/W2158278868","https://openalex.org/W2160067530","https://openalex.org/W2165131254","https://openalex.org/W2165905123","https://openalex.org/W2167509584","https://openalex.org/W2169982856","https://openalex.org/W2171611360","https://openalex.org/W2334782222","https://openalex.org/W2336663587","https://openalex.org/W2415292238","https://openalex.org/W2419084655","https://openalex.org/W2484957131","https://openalex.org/W2487144912","https://openalex.org/W2611866857","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W3043829799","https://openalex.org/W4205326910","https://openalex.org/W4230557482","https://openalex.org/W4233696721","https://openalex.org/W4285719527","https://openalex.org/W6612245137","https://openalex.org/W6616092997","https://openalex.org/W6617752786","https://openalex.org/W6631914715","https://openalex.org/W6634528131","https://openalex.org/W6636083699","https://openalex.org/W6674995601","https://openalex.org/W6683392610","https://openalex.org/W6683935339","https://openalex.org/W6689723076","https://openalex.org/W6775686901","https://openalex.org/W7065010408"],"related_works":["https://openalex.org/W4389475841","https://openalex.org/W2808418668","https://openalex.org/W4241327272","https://openalex.org/W2120406836","https://openalex.org/W1996214847","https://openalex.org/W2903299703","https://openalex.org/W2117282672","https://openalex.org/W4211224558","https://openalex.org/W4281791088","https://openalex.org/W1574958246"],"abstract_inverted_index":{"We":[0],"consider":[1],"the":[2,19,54,69,79,101,135],"classical":[3],"finite-state":[4],"discounted":[5],"Markovian":[6],"decision":[7],"problem,":[8],"and":[9,74,96,124],"we":[10],"introduce":[11],"a":[12,28,57],"new":[13],"policy":[14,24,105],"iteration-like":[15],"algorithm":[16,34,71,93,132],"for":[17,116],"finding":[18],"optimal":[20,41],"Q-factors.":[21],"Instead":[22],"of":[23,31,39,72,103,138],"evaluation":[25],"by":[26],"solving":[27],"linear":[29,120],"system":[30],"equations,":[32],"our":[33,92,131],"involves":[35],"(possibly":[36],"inexact)":[37],"solution":[38],"an":[40],"stopping":[42],"problem.":[43],"This":[44],"problem":[45],"can":[46,64],"be":[47,66],"solved":[48,67],"with":[49,68,107],"simple":[50],"Q-learning":[51,70,113],"iterations,":[52],"in":[53,78,100],"case":[55,80],"where":[56,81,119],"lookup":[58],"table":[59,89],"representation":[60,90],"is":[61],"used;":[62],"it":[63],"also":[65],"Tsitsiklis":[73],"Van":[75],"Roy":[76],"[TsV99],":[77],"feature-based":[82],"Q-factor":[83],"approximations":[84,123],"are":[85,129],"used.":[86],"In":[87],"exact/lookup":[88],"form,":[91],"admits":[94],"asynchronous":[95],"stochastic":[97],"iterative":[98],"implementations,":[99],"spirit":[102],"asynchronous/modified":[104],"iteration,":[106],"lower":[108],"overhead":[109],"advantages":[110],"over":[111],"existing":[112,139],"schemes.":[114],"Furthermore,":[115],"large-scale":[117],"problems,":[118],"basis":[121],"function":[122],"simulation-based":[125],"temporal":[126],"difference":[127],"implementations":[128],"used,":[130],"resolves":[133],"effectively":[134],"inherent":[136],"difficulties":[137],"schemes":[140],"due":[141],"to":[142],"inadequate":[143],"exploration.":[144]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}