{"id":"https://openalex.org/W1497506444","doi":"https://doi.org/10.1109/icmla.2004.1383528","title":"Planning with predictive state representations","display_name":"Planning with predictive state representations","publication_year":2005,"publication_date":"2005-04-06","ids":{"openalex":"https://openalex.org/W1497506444","doi":"https://doi.org/10.1109/icmla.2004.1383528","mag":"1497506444"},"language":"en","primary_location":{"id":"doi:10.1109/icmla.2004.1383528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla.2004.1383528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 International Conference on Machine Learning and Applications, 2004. Proceedings.","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5066781741","display_name":"M. R. James","orcid":"https://orcid.org/0000-0003-2821-0133"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M.R. James","raw_affiliation_strings":["University of Michigan, USA","(University of Michigan)"],"affiliations":[{"raw_affiliation_string":"University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"(University of Michigan)","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046052093","display_name":"Satinder Singh","orcid":"https://orcid.org/0009-0003-3380-7804"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Singh","raw_affiliation_strings":["University of Michigan, USA","Electrical Engineering and Computer Science - Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"University of Michigan, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Electrical Engineering and Computer Science - Computer Science and Engineering","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009722403","display_name":"Michael L. Littman","orcid":"https://orcid.org/0000-0002-5596-1840"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M.L. Littman","raw_affiliation_strings":["Rutgers University, USA","Rutgers, The State University of New Jersey [New Brunswick]"],"affiliations":[{"raw_affiliation_string":"Rutgers University, USA","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Rutgers, The State University of New Jersey [New Brunswick]","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066781741"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":8.3363,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.97447319,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"304","last_page":"311"},"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9868000149726868,"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/T10142","display_name":"Formal Methods in Verification","score":0.9848999977111816,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.7578237652778625},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7449088096618652},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7424933910369873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6850112676620483},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5768693089485168},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5405638813972473},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.5183069109916687},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.5017566680908203},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5013003349304199},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.49921441078186035},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.49355781078338623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4780329167842865},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4509836435317993},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.4265058636665344},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3826921582221985},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35327351093292236},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.35258352756500244},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2748951017856598},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19688349962234497},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.18517765402793884},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.14213961362838745}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.7578237652778625},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7449088096618652},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7424933910369873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6850112676620483},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5768693089485168},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5405638813972473},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.5183069109916687},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.5017566680908203},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5013003349304199},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49921441078186035},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.49355781078338623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4780329167842865},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4509836435317993},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.4265058636665344},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3826921582221985},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35327351093292236},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.35258352756500244},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2748951017856598},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19688349962234497},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.18517765402793884},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.14213961362838745},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmla.2004.1383528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla.2004.1383528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 International Conference on Machine Learning and Applications, 2004. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1491973539","https://openalex.org/W1515891729","https://openalex.org/W2041367235","https://openalex.org/W2099873296","https://openalex.org/W2103019454","https://openalex.org/W2111680853","https://openalex.org/W2117341272","https://openalex.org/W2121863487","https://openalex.org/W2123542217","https://openalex.org/W2158282517","https://openalex.org/W2312609093","https://openalex.org/W2949905447","https://openalex.org/W3011120880","https://openalex.org/W4214717370","https://openalex.org/W6629490593","https://openalex.org/W6631000544","https://openalex.org/W6674711614","https://openalex.org/W6677000785","https://openalex.org/W6678409309","https://openalex.org/W6683084483"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W4323315247","https://openalex.org/W3169161914","https://openalex.org/W3208638985"],"abstract_inverted_index":{"Predictive":[0],"state":[1],"representation":[2],"(PSR)":[3],"models":[4,18],"for":[5,38,47,58],"controlled":[6],"dynamical":[7],"systems":[8],"have":[9],"recently":[10],"been":[11],"proposed":[12],"as":[13,20,94],"an":[14,68],"alternative":[15],"to":[16,64,99],"traditional":[17,89],"such":[19,93],"partially":[21],"observable":[22],"Markov":[23],"decision":[24],"processes":[25],"(POMDPs).":[26],"In":[27],"this":[28],"paper":[29],"we":[30,42,86],"develop":[31],"and":[32],"evaluate":[33,104],"two":[34],"general":[35],"planning":[36,45],"algorithms":[37,46,92,107],"PSR":[39,100],"models.":[40,101],"First,":[41],"show":[43,87],"how":[44,88],"POMDPs":[48,78],"that":[49],"exploit":[50],"the":[51,72],"piecewise":[52],"linear":[53],"property":[54],"of":[55,71,74,112],"value":[56],"functions":[57],"finite-horizon":[59],"problems":[60],"can":[61,96],"be":[62,97],"extended":[63,98],"PSRs.":[65,84],"This":[66],"requires":[67],"interesting":[69],"replacement":[70],"role":[73],"hidden":[75],"nominalstates":[76],"in":[77,83],"with":[79],"linearly":[80],"independent":[81],"predictions":[82],"Second,":[85],"reinforcement":[90],"learning":[91],"Q-learning":[95],"We":[102],"empirically":[103],"both":[105],"our":[106],"on":[108],"a":[109],"standard":[110],"set":[111],"test":[113],"POMDP":[114],"problems.":[115]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}