{"id":"https://openalex.org/W2114501936","doi":null,"title":"Learning Factored Representations for Partially Observable Markov Decision Processes","display_name":"Learning Factored Representations for Partially Observable Markov Decision Processes","publication_year":1999,"publication_date":"1999-11-29","ids":{"openalex":"https://openalex.org/W2114501936","mag":"2114501936"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.36.5074","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.36.5074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gatsby.ucl.ac.uk/publications/papers/07-2000.ps","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/A5009796192","display_name":"Brian Sallans","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4405268824","display_name":"Gatsby Computational Neuroscience Unit","ror":"https://ror.org/0269epf40","country_code":"GB","type":"facility","lineage":["https://openalex.org/I124357947","https://openalex.org/I4405268824","https://openalex.org/I45129253"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["CA","GB"],"is_corresponding":true,"raw_author_name":"Brian Sallans","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Toronto, Canada and Gatsby Computational Neuroscience Unit, University College London, London, UK#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Toronto, Canada and Gatsby Computational Neuroscience Unit, University College London, London, UK#TAB#","institution_ids":["https://openalex.org/I185261750","https://openalex.org/I4405268824","https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009796192"],"corresponding_institution_ids":["https://openalex.org/I185261750","https://openalex.org/I4405268824","https://openalex.org/I45129253"],"apc_list":null,"apc_paid":null,"fwci":1.5095,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.83076364,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"12","issue":null,"first_page":"1050","last_page":"1056"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0005000000237487257,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0,"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/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.925000011920929},{"id":"https://openalex.org/keywords/factored-representation","display_name":"factored representation","score":0.8370000123977661},{"id":"https://openalex.org/keywords/dynamic-bayesian-networks","display_name":"dynamic Bayesian networks","score":0.9419999718666077},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6430000066757202},{"id":"https://openalex.org/keywords/value-function-approximation","display_name":"value function approximation","score":0.8399999737739563},{"id":"https://openalex.org/keywords/online-parameter-learning","display_name":"online parameter learning","score":0.7139999866485596},{"id":"https://openalex.org/keywords/conditional-independence","display_name":"conditional independence","score":0.6370000243186951},{"id":"https://openalex.org/keywords/driving-task","display_name":"driving task","score":0.6690000295639038},{"id":"https://openalex.org/keywords/policy-quality","display_name":"policy quality","score":0.4169999957084656}],"concepts":[{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.6514403820037842},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6198137998580933},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5947995185852051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.582046389579773},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.574164867401123},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5550485253334045},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5125360488891602},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.5019681453704834},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4943399429321289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.473890483379364},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.46395984292030334},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4559178948402405},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42754819989204407},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.42049339413642883},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.41742849349975586},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.4126972556114197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3968052268028259},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.39310333132743835},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.31984585523605347},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31660300493240356},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09778892993927002},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.36.5074","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.36.5074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gatsby.ucl.ac.uk/publications/papers/07-2000.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.64.9224","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.64.9224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gatsby.ucl.ac.uk/publications/papers/07-2000.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.84.244","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.84.244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://members.chello.at/hoebertz-sallans/sallans/papers/nips99.pdf","raw_type":"text"},{"id":"mag:2114501936","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/1754-learning-factored-representations-for-partially-observable-markov-decision-processes.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":18,"referenced_works":["https://openalex.org/W1516111018","https://openalex.org/W1520448186","https://openalex.org/W1528056001","https://openalex.org/W1539216098","https://openalex.org/W1575388622","https://openalex.org/W1583380718","https://openalex.org/W1588316674","https://openalex.org/W1657674574","https://openalex.org/W1980452149","https://openalex.org/W2020294948","https://openalex.org/W2034725503","https://openalex.org/W2044375425","https://openalex.org/W2052117683","https://openalex.org/W2083380015","https://openalex.org/W2105594594","https://openalex.org/W2112197391","https://openalex.org/W2146398222","https://openalex.org/W2159080219"],"related_works":["https://openalex.org/W2883163772","https://openalex.org/W1554120378","https://openalex.org/W2055060379","https://openalex.org/W1554015367","https://openalex.org/W7097804539","https://openalex.org/W2520065132","https://openalex.org/W3004707083","https://openalex.org/W2136808757","https://openalex.org/W2408394588","https://openalex.org/W2154347416"],"abstract_inverted_index":{"The":[0,29,48,75,108],"problem":[1,135],"of":[2,51,60,102,136],"reinforcement":[3],"learning":[4,67,131],"in":[5],"a":[6,12,70,115,118],"non-Markov":[7],"environment":[8],"is":[9],"explored":[10],"using":[11,117],"dynamic":[13,109],"Bayesian":[14,110],"network,":[15],"where":[16],"conditional":[17],"independence":[18],"assumptions":[19],"between":[20],"random":[21],"variables":[22],"are":[23,31,36,64],"compactly":[24],"represented":[25],"by":[26,66],"network":[27,111],"parameters.":[28,127],"parameters":[30],"learned":[32],"on-line,":[33],"and":[34,41,53,81],"approximations":[35,56],"used":[37],"to":[38,42,68,85,95,114],"perform":[39,86],"inference":[40,52],"compute":[43],"the":[44,58,61,89,100,106,134],"optimal":[45],"value":[46,54,77],"function.":[47],"relative":[49],"effects":[50],"function":[55,78],"on":[57,105],"quality":[59],"final":[62],"policy":[63],"investigated,":[65],"solve":[69],"moderately":[71],"difficult":[72],"driving":[73],"task.":[74,107],"two":[76],"approximations,":[79],"linear":[80],"quadratic,":[82],"were":[83],"found":[84],"similarly,":[87],"but":[88],"quadratic":[90],"model":[91,116],"was":[92],"more":[93],"sensitive":[94],"initialization.":[96],"Both":[97],"performed":[98,112],"below":[99],"level":[101],"human":[103],"performance":[104],"comparably":[113],"localist":[119],"hidden":[120],"state":[121],"representation,":[122],"while":[123],"requiring":[124],"exponentially":[125],"fewer":[126],"1":[128],"Introduction":[129],"Reinforcement":[130],"(RL)":[132],"addresses":[133],"learni...":[137]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2016-06-24T00:00:00"}