{"id":"https://openalex.org/W2139302369","doi":null,"title":"Learning first-order Markov models for control","display_name":"Learning first-order Markov models for control","publication_year":2004,"publication_date":"2004-12-01","ids":{"openalex":"https://openalex.org/W2139302369","mag":"2139302369"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.875.3253","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.875.3253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://papers.nips.cc/paper/2569-learning-first-order-markov-models-for-control.pdf","raw_type":"text"},"volume":null,"type":"article","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/A5049349154","display_name":"Pieter Abbeel","orcid":"https://orcid.org/0009-0007-0628-9932","observed_orcids":["https://orcid.org/0009-0007-0628-9932"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pieter Abbeel","raw_affiliation_strings":["[Computer Science Department, Stanford University, Stanford, CA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Computer Science Department, Stanford University, Stanford, CA]","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102617494","display_name":"Andrew Y. Ng","orcid":"https://orcid.org/0000-0001-5547-3196","observed_orcids":["https://orcid.org/0000-0001-5547-3196"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Y. Ng","raw_affiliation_strings":["[Computer Science Department, Stanford University, Stanford, CA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Computer Science Department, Stanford University, Stanford, CA]","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.3496,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.84749413,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"17","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9771000146865845,"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":0.9771000146865845,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.009800000116229057,"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":0.0032999999821186066,"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/first-order-markov-model","display_name":"first-order Markov model","score":0.9940000176429749},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.9700000286102295},{"id":"https://openalex.org/keywords/parameter-learning","display_name":"parameter learning","score":0.753000020980835},{"id":"https://openalex.org/keywords/higher-order-interactions","display_name":"higher-order interactions","score":0.7440000176429749},{"id":"https://openalex.org/keywords/conditional-independence","display_name":"conditional independence","score":0.6650000214576721},{"id":"https://openalex.org/keywords/maximum-likelihood-estimation","display_name":"maximum likelihood estimation","score":0.7129999995231628},{"id":"https://openalex.org/keywords/sequential-data-modeling","display_name":"sequential data modeling","score":0.5640000104904175},{"id":"https://openalex.org/keywords/optimization-criteria","display_name":"optimization criteria","score":0.5410000085830688}],"concepts":[{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.729609489440918},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.6667523384094238},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.6465674042701721},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6015613079071045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5850675702095032},{"id":"https://openalex.org/C196956702","wikidata":"https://www.wikidata.org/wiki/Q6795829","display_name":"Maximum-entropy Markov model","level":5,"score":0.5821509957313538},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5651763677597046},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.502823531627655},{"id":"https://openalex.org/C189973286","wikidata":"https://www.wikidata.org/wiki/Q176695","display_name":"Markov property","level":4,"score":0.49446892738342285},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4799825847148895},{"id":"https://openalex.org/C106666656","wikidata":"https://www.wikidata.org/wiki/Q6771323","display_name":"Markov kernel","level":5,"score":0.42161881923675537},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35161542892456055},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34329959750175476},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30116793513298035},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14647704362869263}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.875.3253","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.875.3253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://papers.nips.cc/paper/2569-learning-first-order-markov-models-for-control.pdf","raw_type":"text"},{"id":"mag:2139302369","doi":null,"is_oa":false,"landing_page_url":"http://ai.stanford.edu/~ang/papers/nips04-controlmodel.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":null,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.7799999713897705,"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1537659559","https://openalex.org/W1541680420","https://openalex.org/W1594216983","https://openalex.org/W1600813180","https://openalex.org/W2036931518","https://openalex.org/W2075201173","https://openalex.org/W2099111195","https://openalex.org/W2121517924","https://openalex.org/W2125838338","https://openalex.org/W2148603752","https://openalex.org/W2159080219","https://openalex.org/W2161521419","https://openalex.org/W2163614729","https://openalex.org/W2168359464","https://openalex.org/W2567948266"],"related_works":["https://openalex.org/W2130519334","https://openalex.org/W2152431402","https://openalex.org/W1901061646","https://openalex.org/W2048052024","https://openalex.org/W1558734078","https://openalex.org/W2015616314","https://openalex.org/W2026084326","https://openalex.org/W2964179600","https://openalex.org/W1579169570","https://openalex.org/W2245070833","https://openalex.org/W2130105540","https://openalex.org/W1896420489","https://openalex.org/W3124353122","https://openalex.org/W1983191662","https://openalex.org/W2101789897","https://openalex.org/W2027976015","https://openalex.org/W2020246581","https://openalex.org/W2965457720","https://openalex.org/W1413305739","https://openalex.org/W2098687269"],"abstract_inverted_index":{"First-order":[0],"Markov":[1,17,25,33,95,137],"models":[2,122],"have":[3],"been":[4],"successfully":[5],"applied":[6],"to":[7,120],"many":[8,53],"prob-lems,":[9],"for":[10,52,85,91],"example":[11],"in":[12,152],"modeling":[13,20],"sequential":[14],"data":[15],"using":[16,23,135],"chains,":[18],"and":[19,63,117],"control":[21,156],"problems":[22,157],"the":[24,40,47,55,67,78,132,144,159],"decision":[26],"processes":[27],"(MDP)":[28],"formalism.":[29],"If":[30],"a":[31,65,93,153],"first-order":[32,48,56,94,136],"model\u2019s":[34],"parameters":[35,84,161],"are":[36,60,162],"estimated":[37,163],"from":[38,114,164],"data,":[39],"standard":[41],"maximum":[42,115,149],"likelihood":[43,150],"estimator":[44],"considers":[45],"only":[46],"(single-step)":[49],"transitions.":[50],"But":[51],"problems,":[54],"conditional":[57],"independence":[58],"assumptions":[59],"not":[61],"satisfied,":[62],"as":[64],"re-sult":[66],"higher":[68,102],"order":[69,103],"transition":[70],"probabilities":[71],"may":[72],"be":[73],"poorly":[74],"approximated.":[75],"Motivated":[76],"by":[77],"problem":[79],"of":[80,134,155],"learning":[81,92],"an":[82,89,110],"MDP\u2019s":[83,160],"control,":[86],"we":[87],"propose":[88],"algorithm":[90,108,146],"model":[96],"that":[97,123],"ex-plicitly":[98],"takes":[99],"into":[100],"account":[101],"interactions":[104],"during":[105],"training.":[106],"Our":[107,139],"uses":[109],"optimization":[111],"criterion":[112],"different":[113],"likeli-hood,":[116],"allows":[118],"us":[119],"learn":[121],"capture":[124],"longer":[125],"range":[126],"effects,":[127],"but":[128],"without":[129],"giving":[130],"up":[131],"benefits":[133],"models.":[138],"experimental":[140],"results":[141],"also":[142],"show":[143],"new":[145],"outperforming":[147],"conven-tional":[148],"estimation":[151],"number":[154],"where":[158],"data.":[165],"1":[166]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-10-17T09:40:24.721904","created_date":"2025-10-10T00:00:00"}