{"id":"https://openalex.org/W2153947321","doi":null,"title":"Reinforcement Learning Methods for Continuous-Time Markov Decision Problems","display_name":"Reinforcement Learning Methods for Continuous-Time Markov Decision Problems","publication_year":1994,"publication_date":"1994-01-01","ids":{"openalex":"https://openalex.org/W2153947321","mag":"2153947321"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.32.9030","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.32.9030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.cs.umass.edu/pub/anw/pub/bradtke/bradtke-duff-NIPS94.ps.gz","raw_type":"text"},"volume":null,"type":"article","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/A5081885151","display_name":"Steven J. Bradtke","orcid":null,"observed_orcids":[]},"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":"Steven J. Bradtke","raw_affiliation_strings":["Comput. Sci. Dept., Univ. of Massachusetts, Amherst, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Comput. Sci. Dept., Univ. of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":null,"display_name":"Michael O. Duff","orcid":null,"observed_orcids":[]},"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":"Michael O. Duff","raw_affiliation_strings":["Comput. Sci. Dept., Univ. of Massachusetts, Amherst, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Comput. Sci. Dept., Univ. of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":1.8811,"has_fulltext":false,"cited_by_count":263,"citation_normalized_percentile":{"value":0.87246983,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"7","issue":null,"first_page":"393","last_page":"400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9824000000953674,"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":0.9824000000953674,"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":0.015200000256299973,"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"}},{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.0008999999845400453,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.8080000281333923},{"id":"https://openalex.org/keywords/semi-markov-decision-process","display_name":"semi-Markov decision process","score":0.8939999938011169},{"id":"https://openalex.org/keywords/continuous-time-markov-decision-processes","display_name":"continuous-time Markov decision processes","score":0.9340000152587891},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"stochastic approximation","score":0.9990000128746033},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"temporal difference learning","score":0.7639999985694885},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/real-time-dynamic-programming","display_name":"real-time dynamic programming","score":0.9919999837875366},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.9369999766349792},{"id":"https://openalex.org/keywords/optimal-control","display_name":"optimal control","score":0.9240000247955322},{"id":"https://openalex.org/keywords/queueing-systems","display_name":"queueing systems","score":0.9950000047683716}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8966712951660156},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7734149694442749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6499170064926147},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5734043121337891},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5548626780509949},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5461229085922241},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5175296664237976},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4967392086982727},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4599233567714691},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.4583546221256256},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44683507084846497},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.4425990879535675},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.44011884927749634},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.43310296535491943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33992069959640503},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33146584033966064},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24495339393615723},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23783203959465027},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.32.9030","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.32.9030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.cs.umass.edu/pub/anw/pub/bradtke/bradtke-duff-NIPS94.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.55.4868","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.55.4868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.cs.umass.edu/pub/anw/pub/duff/NIPS94a-final.ps.Z","raw_type":"text"},{"id":"mag:2153947321","doi":null,"is_oa":false,"landing_page_url":"http://papers.nips.cc/paper/889-reinforcement-learning-methods-for-continuous-time-markov-decision-problems.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"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":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W6614468","https://openalex.org/W1545148916","https://openalex.org/W1826343992","https://openalex.org/W1991513691","https://openalex.org/W2009533501","https://openalex.org/W2045374782","https://openalex.org/W2100677568","https://openalex.org/W2134300276","https://openalex.org/W2165131254","https://openalex.org/W2534068475","https://openalex.org/W3011120880"],"related_works":["https://openalex.org/W2292411112","https://openalex.org/W2907902612","https://openalex.org/W2075754841","https://openalex.org/W4283461801","https://openalex.org/W274497311","https://openalex.org/W7095618355","https://openalex.org/W1985560493","https://openalex.org/W3136570838","https://openalex.org/W7099297714","https://openalex.org/W7111386121"],"abstract_inverted_index":{"Semi-Markov":[0],"Decision":[1,11,28,53,76],"Problems":[2,54],"are":[3,43],"continuous":[4],"time":[5,9],"generalizations":[6],"of":[7,15,26,34,74,88,103,117,125],"discrete":[8],"Markov":[10,27],"Problems.":[12,77],"A":[13,115],"number":[14,116],"reinforcement":[16,118],"learning":[17,119],"algorithms":[18,64,81,108,120],"have":[19,132],"been":[20,133],"developed":[21,134],"recently":[22,135],"for":[23,93],"the":[24,32,72,86,90,123],"solution":[25,73],"Problems,":[29],"based":[30,121],"on":[31,122],"ideas":[33,124],"asynchronous":[35,126],"dynamic":[36,127],"programming":[37,128],"and":[38,46,55,129],"stochastic":[39,130],"approximation.":[40],"Among":[41],"these":[42,80,107],"TD(),":[44],"Q-learning,":[45],"Real-time":[47],"Dynamic":[48],"Programming.":[49],"After":[50],"reviewing":[51],"semi-Markov":[52,75],"Bellman's":[56],"optimality":[57],"equation":[58],"in":[59],"that":[60],"context,":[61],"we":[62],"propose":[63],"similar":[65],"to":[66,71,85],"those":[67],"named":[68],"above,":[69],"adapted":[70],"We":[78,98],"demonstrate":[79],"by":[82],"applying":[83],"them":[84],"problem":[87],"determining":[89],"optimal":[91],"control":[92],"a":[94,101],"simple":[95],"queueing":[96],"system.":[97],"conclude":[99],"with":[100],"discussion":[102],"circumstances":[104],"under":[105],"which":[106],"may":[109],"be":[110],"usefully":[111],"applied.":[112],"1":[113],"Introduction":[114],"approximation":[131],"for...":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":14}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}