{"id":"https://openalex.org/W7318248","doi":null,"title":"Learning and Solving Partially Observable Markov Decision Processes","display_name":"Learning and Solving Partially Observable Markov Decision Processes","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W7318248","mag":"7318248"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.711.7916","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.711.7916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.bgu.ac.il/%7Eshanigu/Publications/Dissertation.4.pdf","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/A5006317361","display_name":"Guy Shani","orcid":"https://orcid.org/0000-0003-4131-0382","observed_orcids":["https://orcid.org/0000-0003-4131-0382","https://orcid.org/0000-0002-3655-7148"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Guy Shani","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4131-0382","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5006317361"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.00111831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9970999956130981,"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":0.9970999956130981,"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":0.001500000013038516,"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":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.9779999852180481},{"id":"https://openalex.org/keywords/model-free-learning","display_name":"model-free learning","score":0.703000009059906},{"id":"https://openalex.org/keywords/model-based-learning","display_name":"model-based learning","score":0.9440000057220459},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.5410000085830688},{"id":"https://openalex.org/keywords/stochastic-environments","display_name":"stochastic environments","score":0.4819999933242798},{"id":"https://openalex.org/keywords/partial-observability","display_name":"partial observability","score":0.8069999814033508},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.460999995470047}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7833734750747681},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595218420028687},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.6727510690689087},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.5760252475738525},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.575283944606781},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5683867931365967},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5094686150550842},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5062164664268494},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4558715522289276},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4394802153110504},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4387565553188324},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43408524990081787},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.35886260867118835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3444845676422119},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.29888492822647095},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27477991580963135},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.21047711372375488},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13332754373550415},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.711.7916","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.711.7916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.bgu.ac.il/%7Eshanigu/Publications/Dissertation.4.pdf","raw_type":"text"},{"id":"mag:7318248","doi":null,"is_oa":false,"landing_page_url":"https://www.bgu.ac.il/~shanigu/Publications/Dissertation.4.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"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":83,"referenced_works":["https://openalex.org/W6242441","https://openalex.org/W11162148","https://openalex.org/W32785352","https://openalex.org/W131709709","https://openalex.org/W159191692","https://openalex.org/W161873470","https://openalex.org/W183139520","https://openalex.org/W246998018","https://openalex.org/W1483935885","https://openalex.org/W1484113995","https://openalex.org/W1486632395","https://openalex.org/W1487408605","https://openalex.org/W1494689917","https://openalex.org/W1497506444","https://openalex.org/W1498235675","https://openalex.org/W1499371387","https://openalex.org/W1517260920","https://openalex.org/W1532688806","https://openalex.org/W1539216098","https://openalex.org/W1540337045","https://openalex.org/W1553173248","https://openalex.org/W1555477527","https://openalex.org/W1555801537","https://openalex.org/W1575388622","https://openalex.org/W1580557482","https://openalex.org/W1581055761","https://openalex.org/W1583380718","https://openalex.org/W1587703211","https://openalex.org/W1594297126","https://openalex.org/W1595634327","https://openalex.org/W1640774615","https://openalex.org/W1657542410","https://openalex.org/W1657674574","https://openalex.org/W1687873425","https://openalex.org/W1701684472","https://openalex.org/W1801737117","https://openalex.org/W1831612509","https://openalex.org/W2009533501","https://openalex.org/W2028145673","https://openalex.org/W2032100464","https://openalex.org/W2048226872","https://openalex.org/W2052117683","https://openalex.org/W2057399676","https://openalex.org/W2061226732","https://openalex.org/W2080245272","https://openalex.org/W2080267935","https://openalex.org/W2096132608","https://openalex.org/W2099873296","https://openalex.org/W2107726111","https://openalex.org/W2108519123","https://openalex.org/W2110962519","https://openalex.org/W2113013121","https://openalex.org/W2113913482","https://openalex.org/W2116459397","https://openalex.org/W2120406836","https://openalex.org/W2121733891","https://openalex.org/W2121863487","https://openalex.org/W2123542217","https://openalex.org/W2133077903","https://openalex.org/W2134802714","https://openalex.org/W2138089556","https://openalex.org/W2144283793","https://openalex.org/W2149126181","https://openalex.org/W2150459019","https://openalex.org/W2153175335","https://openalex.org/W2154384352","https://openalex.org/W2158282517","https://openalex.org/W2158548602","https://openalex.org/W2158907787","https://openalex.org/W2159498728","https://openalex.org/W2160067530","https://openalex.org/W2164056559","https://openalex.org/W2166610875","https://openalex.org/W2166696997","https://openalex.org/W2167435507","https://openalex.org/W2168359464","https://openalex.org/W2169294731","https://openalex.org/W2172246523","https://openalex.org/W2334782222","https://openalex.org/W2341171179","https://openalex.org/W2763384692","https://openalex.org/W2912185451","https://openalex.org/W2963889160"],"related_works":["https://openalex.org/W1539216098","https://openalex.org/W7098174039","https://openalex.org/W52153049","https://openalex.org/W1526144783","https://openalex.org/W7095232061","https://openalex.org/W4399828133","https://openalex.org/W7101108054","https://openalex.org/W122144300","https://openalex.org/W1508297888","https://openalex.org/W1558845053"],"abstract_inverted_index":{"Partially":[0],"Observable":[1],"Markov":[2],"Decision":[3],"Processes":[4],"(POMDPs)":[5],"provide":[6,102],"a":[7,14,76,142,152,161],"rich":[8],"representation":[9],"for":[10,29,43,80,84],"agents":[11],"acting":[12],"in":[13,107,131,146],"stochastic":[15],"domain":[16],"under":[17],"partial":[18],"observability.":[19],"POMDPs":[20,38,63,86],"optimally":[21,64],"balance":[22],"key":[23],"properties":[24],"such":[25],"as":[26,90,105],"the":[27,32,52,59,108,137,155,166,172],"need":[28],"information":[30],"and":[31,55,144],"sum":[33],"of":[34,78,154,171],"collected":[35],"rewards.":[36],"However,":[37],"are":[39,87],"difficult":[40,49],"to":[41,50,101,113,116,177],"use":[42],"two":[44],"reasons;":[45],"first,":[46],"it":[47],"is":[48,65,128,157],"obtain":[51],"environment":[53,60,109,156],"dynamics":[54],"second,":[56],"even":[57],"given":[58],"dynamics,":[61],"solving":[62],"intractable.":[66],"This":[67,126],"dissertation":[68,173],"deals":[69],"with":[70,75,160,165],"both":[71],"difficulties.":[72],"We":[73,95,111],"begin":[74],"number":[77],"methods":[79,99],"learning":[81,85],"POMDPs.":[82,180],"Methods":[83],"usually":[88],"categorized":[89],"either":[91],"model-free":[92,98,118,138],"or":[93],"model-based.":[94],"show":[96],"how":[97,115],"fail":[100],"good":[103],"policies":[104],"noise":[106],"increases.":[110],"continue":[112],"suggest":[114],"transform":[117],"into":[119],"model-based":[120],"methods,":[121],"thus":[122],"improving":[123],"their":[124],"solution.":[125],"transformation":[127],"first":[129],"demonstrated":[130],"an":[132,147],"offline":[133],"process":[134],"\u2014":[135,150],"after":[136],"method":[139],"has":[140],"computed":[141],"policy,":[143],"then":[145],"online":[148],"setting":[149],"where":[151],"model":[153],"learned":[158],"together":[159],"policy":[162],"through":[163],"interactions":[164],"environment.":[167],"The":[168],"second":[169],"part":[170],"focuses":[174],"on":[175],"ways":[176],"solve":[178],"predefined":[179],"Point-":[181]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}