{"id":"https://openalex.org/W2113501460","doi":"https://doi.org/10.1162/089976600300015961","title":"Reinforcement Learning in Continuous Time and Space","display_name":"Reinforcement Learning in Continuous Time and Space","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W2113501460","doi":"https://doi.org/10.1162/089976600300015961","mag":"2113501460","pmid":"https://pubmed.ncbi.nlm.nih.gov/10636940"},"language":"en","primary_location":{"id":"doi:10.1162/089976600300015961","is_oa":false,"landing_page_url":"https://doi.org/10.1162/089976600300015961","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5004840638","display_name":"Kenji Doya","orcid":"https://orcid.org/0000-0002-2446-6820"},"institutions":[{"id":"https://openalex.org/I4210158934","display_name":"Research Organization of Information and Systems","ror":"https://ror.org/04p4e8t29","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kenji Doya","raw_affiliation_strings":["ATR Human Information Processing Research Laboratories, Soraku, Kyoto 619-0288, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Human Information Processing Research Laboratories, Soraku, Kyoto 619-0288, Japan","institution_ids":["https://openalex.org/I4210158934"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5004840638"],"corresponding_institution_ids":["https://openalex.org/I4210158934"],"apc_list":null,"apc_paid":null,"fwci":19.6496,"has_fulltext":false,"cited_by_count":985,"citation_normalized_percentile":{"value":0.99356309,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"12","issue":"1","first_page":"219","last_page":"245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9732000231742859,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hamilton\u2013jacobi\u2013bellman-equation","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","score":0.8032176494598389},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7655755281448364},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.7085764408111572},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.5823149681091309},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.5580704212188721},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.51394122838974},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.49419882893562317},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4531949758529663},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4486501216888428},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44754448533058167},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4389657974243164},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.42299267649650574},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.4180125594139099},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.4123189449310303},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3745630383491516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23020800948143005}],"concepts":[{"id":"https://openalex.org/C196978813","wikidata":"https://www.wikidata.org/wiki/Q3302775","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","level":3,"score":0.8032176494598389},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7655755281448364},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.7085764408111572},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.5823149681091309},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.5580704212188721},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.51394122838974},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.49419882893562317},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4531949758529663},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4486501216888428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44754448533058167},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4389657974243164},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.42299267649650574},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4180125594139099},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.4123189449310303},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3745630383491516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23020800948143005},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008960","descriptor_name":"Models, Psychological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008960","descriptor_name":"Models, Psychological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008960","descriptor_name":"Models, Psychological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1162/089976600300015961","is_oa":false,"landing_page_url":"https://doi.org/10.1162/089976600300015961","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:10636940","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/10636940","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural computation","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.38.7461","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.38.7461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://meta.rad.atr.co.jp/doya/papers/nc99.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.646.2166","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.646.2166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://homes.cs.washington.edu/~todorov/courses/amath579/reading/Continuous.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W20823384","https://openalex.org/W92805021","https://openalex.org/W774034202","https://openalex.org/W1515851193","https://openalex.org/W1547105496","https://openalex.org/W1558902221","https://openalex.org/W1594216983","https://openalex.org/W1646707810","https://openalex.org/W1813512609","https://openalex.org/W1831990963","https://openalex.org/W1966195676","https://openalex.org/W2041367235","https://openalex.org/W2051269406","https://openalex.org/W2080759927","https://openalex.org/W2091565802","https://openalex.org/W2098432798","https://openalex.org/W2098607794","https://openalex.org/W2100644648","https://openalex.org/W2100677568","https://openalex.org/W2101533993","https://openalex.org/W2105038027","https://openalex.org/W2105078254","https://openalex.org/W2106814169","https://openalex.org/W2106849842","https://openalex.org/W2107726111","https://openalex.org/W2112246162","https://openalex.org/W2112940296","https://openalex.org/W2117341272","https://openalex.org/W2121832485","https://openalex.org/W2124175081","https://openalex.org/W2125510930","https://openalex.org/W2135094859","https://openalex.org/W2139418546","https://openalex.org/W2142377262","https://openalex.org/W2142592520","https://openalex.org/W2148112459","https://openalex.org/W2148173263","https://openalex.org/W2153947321","https://openalex.org/W2162617871","https://openalex.org/W2166356462","https://openalex.org/W2167647761","https://openalex.org/W2168342951","https://openalex.org/W2169022337","https://openalex.org/W2172123610","https://openalex.org/W2198041288","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3011120880","https://openalex.org/W3041202696"],"related_works":["https://openalex.org/W4255265352","https://openalex.org/W4239477580","https://openalex.org/W2921905705","https://openalex.org/W1632524629","https://openalex.org/W2902017027","https://openalex.org/W2110376385","https://openalex.org/W2766998270","https://openalex.org/W2950982235","https://openalex.org/W2052286527","https://openalex.org/W4306892756"],"abstract_inverted_index":{"This":[0,260],"article":[1],"presents":[2],"a":[3,12,59,104,110,116,137,159,165,189,214,230,255,273],"reinforcement":[4],"learning":[5],"framework":[6],"for":[7,26,34],"continuous-time":[8,60],"dynamical":[9],"systems":[10],"without":[11],"priori":[13],"discretization":[14],"of":[15,44,49,58,62,113,128,151,163,191],"time,":[16],"state,":[17],"and":[18,38,75,81,90,103,125,228,241],"action.":[19],"Based":[20],"on":[21,71,246],"the":[22,42,56,63,85,114,122,126,129,146,152,175,179,184,198,205,210,225,269],"Hamilton-Jacobi-Bellman":[23],"(HJB)":[24],"equation":[25],"infinite-horizon,":[27],"discounted":[28],"reward":[29],"problems,":[30],"we":[31],"derive":[32],"algorithms":[33,92,154,250],"estimating":[35],"value":[36,50,123,231],"functions":[37],"improving":[39],"policies":[40],"with":[41,84,168,213,272],"use":[43],"function":[45,51,232],"approximators.":[46],"The":[47,134,149,249],"process":[48],"estimation":[52],"is":[53,132,142,155,172,181,238,262],"formulated":[54,144],"as":[55],"minimization":[57],"form":[61],"temporal":[64],"difference":[65],"(TD)":[66],"error.":[67],"Update":[68],"methods":[69],"based":[70,245],"backward":[72],"Euler":[73,247],"approximation":[74],"exponential":[76,235],"eligibility":[77,236],"traces":[78,237],"are":[79,93,251],"derived,":[80],"their":[82],"correspondences":[83],"conventional":[86,199],"residual":[87],"gradient,":[88],"TD(0),":[89],"TD(lambda)":[91],"shown.":[94],"For":[95],"policy":[96,207,212,271],"improvement,":[97],"two":[98],"methods-a":[99],"continuous":[100,185,206],"actor-critic":[101,186,201,226],"method":[102,187],"value-gradient-based":[105,211,270],"greedy":[106],"policy-are":[107],"formulated.":[108],"As":[109],"special":[111],"case":[112],"latter,":[115],"nonlinear":[117,160],"feedback":[118],"control":[119,161],"law":[120],"using":[121,234,268],"gradient":[124],"model":[127,219],"input":[130],"gain":[131],"derived.":[133],"advantage":[135],"updating,":[136],"model-free":[138],"algorithm":[139],"derived":[140],"previously,":[141],"also":[143],"in":[145,158,174,188,254,264],"HJB-based":[147],"framework.":[148],"performance":[150],"proposed":[153],"first":[156],"tested":[157,253],"task":[162,180,261],"swinging":[164],"pendulum":[166],"up":[167],"limited":[169],"torque.":[170],"It":[171],"shown":[173],"simulations":[176],"that":[177,244],"(1)":[178],"accomplished":[182,263],"by":[183,197],"number":[190],"trials":[192,267],"several":[193,221,265],"times":[194,222],"fewer":[195],"than":[196,224,243],"discrete":[200],"method;":[202,227],"(2)":[203],"among":[204],"update":[208,233],"methods,":[209],"known":[215],"or":[216],"learned":[217,274],"dynamic":[218,275],"performs":[220],"better":[223],"(3)":[229],"more":[239],"efficient":[240],"stable":[242],"approximation.":[248],"then":[252],"higher-dimensional":[256],"task:":[257],"cart-pole":[258],"swing-up.":[259],"hundred":[266],"model.":[276]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":36},{"year":2024,"cited_by_count":41},{"year":2023,"cited_by_count":44},{"year":2022,"cited_by_count":40},{"year":2021,"cited_by_count":70},{"year":2020,"cited_by_count":98},{"year":2019,"cited_by_count":70},{"year":2018,"cited_by_count":45},{"year":2017,"cited_by_count":41},{"year":2016,"cited_by_count":33},{"year":2015,"cited_by_count":35},{"year":2014,"cited_by_count":49},{"year":2013,"cited_by_count":40},{"year":2012,"cited_by_count":41}],"updated_date":"2026-05-31T08:46:17.908082","created_date":"2025-10-10T00:00:00"}