{"id":"https://openalex.org/W162215616","doi":null,"title":"Incremental least squares policy iteration for POMDPs","display_name":"Incremental least squares policy iteration for POMDPs","publication_year":2006,"publication_date":"2006-07-16","ids":{"openalex":"https://openalex.org/W162215616","mag":"162215616"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.330.2918","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.2918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.ee.duke.edu/~xjliao/paper/ILSPI_AAAI06_final.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/A5024453724","display_name":"Hui Li","orcid":"https://orcid.org/0000-0001-8310-7169","observed_orcids":["https://orcid.org/0000-0001-8310-7169","https://orcid.org/0009-0007-6292-3707"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hui Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke university, Durham, NC"],"raw_orcid":"https://orcid.org/0000-0001-8310-7169","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke university, Durham, NC","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109304035","display_name":"Xuejun Liao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuejun Liao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke university, Durham, NC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke university, Durham, NC","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016448581","display_name":"Lawrence Carin","orcid":"https://orcid.org/0000-0001-6277-7948","observed_orcids":["https://orcid.org/0000-0001-6277-7948"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lawrence Carin","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke university, Durham, NC"],"raw_orcid":"https://orcid.org/0000-0001-6277-7948","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke university, Durham, NC","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":0.7611,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7649859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1167","last_page":"1172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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":0.00139999995008111,"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/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":0.9800000190734863},{"id":"https://openalex.org/keywords/value-function-approximation","display_name":"value function approximation","score":0.7289999723434448},{"id":"https://openalex.org/keywords/basis-function-selection","display_name":"basis function selection","score":0.7300000190734863},{"id":"https://openalex.org/keywords/optimal-control","display_name":"optimal control","score":0.35199999809265137}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7729387879371643},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6598340272903442},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5818595886230469},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.54994136095047},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5178632736206055},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5064369440078735},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4946136176586151},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49269846081733704},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4772612750530243},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4609743654727936},{"id":"https://openalex.org/C5917680","wikidata":"https://www.wikidata.org/wiki/Q2621825","display_name":"Basis function","level":2,"score":0.45792609453201294},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4302249550819397},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.41958314180374146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3925938010215759},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3311140537261963},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29986387491226196},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09563180804252625},{"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.330.2918","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.2918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.ee.duke.edu/~xjliao/paper/ILSPI_AAAI06_final.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.530.1353","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.530.1353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aaai.org/Papers/AAAI/2006/AAAI06-183.pdf","raw_type":"text"},{"id":"mag:162215616","doi":null,"is_oa":false,"landing_page_url":"http://ece.duke.edu/~lcarin/increLSPI_aaai06_12.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306420577","display_name":"National Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"National Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W90673796","https://openalex.org/W1515851193","https://openalex.org/W1532688806","https://openalex.org/W1555477527","https://openalex.org/W1831612509","https://openalex.org/W2028145673","https://openalex.org/W2034725503","https://openalex.org/W2044375425","https://openalex.org/W2046577860","https://openalex.org/W2074232820","https://openalex.org/W2099833070","https://openalex.org/W2101421095","https://openalex.org/W2109393574","https://openalex.org/W2121863487","https://openalex.org/W2134802714","https://openalex.org/W2149476049","https://openalex.org/W2168359464","https://openalex.org/W2341171179","https://openalex.org/W2963889160"],"related_works":["https://openalex.org/W1528120147","https://openalex.org/W2585510354","https://openalex.org/W2109393574","https://openalex.org/W1864896197","https://openalex.org/W3001911564","https://openalex.org/W1619458041","https://openalex.org/W1508297888","https://openalex.org/W2137486584","https://openalex.org/W7099970765","https://openalex.org/W2130599357"],"abstract_inverted_index":{"We":[0,72],"present":[1],"a":[2,29,88,112],"new":[3],"algorithm,":[4],"called":[5],"incremental":[6],"least":[7],"squares":[8],"policy":[9,17,46,82,114],"iteration":[10,115],"(ILSPI),":[11],"for":[12,18],"finding":[13],"the":[14,33,39,61,65,81,97,102,125],"infinite-horizon":[15,34],"sta-tionary":[16],"partially":[19],"observable":[20],"Markov":[21],"decision":[22],"pro-cesses":[23],"(POMDPs).":[24],"The":[25,117],"ILSPI":[26,103,126],"algorithm":[27,62],"computes":[28],"basis":[30,56,79],"representation":[31],"of":[32,41,54,90,135],"value":[35],"function":[36],"by":[37,60,75],"min-imizing":[38],"square":[40],"Bellman":[42,66],"residual":[43,67],"and":[44,138],"performs":[45],"improvement":[47],"in":[48,133],"reachable":[49,98],"belief":[50,93,99,107],"states.":[51],"A":[52],"number":[53],"opti-mal":[55],"functions":[57],"are":[58],"determined":[59,78],"to":[63,129],"mini-mize":[64],"incrementally,":[68],"via":[69],"efficient":[70],"compu-tations.":[71],"show":[73,123],"that,":[74],"using":[76],"optimally":[77],"functions,":[80],"can":[83],"be":[84],"improved":[85],"successively":[86],"on":[87,106,119],"set":[89],"most":[91],"probable":[92],"points":[94],"sampled":[95],"from":[96],"set.":[100],"As":[101],"is":[104],"based":[105],"sample":[108],"points,":[109],"it":[110],"represents":[111],"point-based":[113],"method.":[116],"results":[118],"four":[120],"benchmark":[121],"problems":[122],"that":[124],"compares":[127],"competitively":[128],"its":[130],"value-iteration":[131],"counterparts":[132],"terms":[134],"both":[136],"performance":[137],"computational":[139],"efficiency.":[140]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-09-29T14:09:16.559479","created_date":"2016-06-24T00:00:00"}