{"id":"https://openalex.org/W2129502467","doi":"https://doi.org/10.1109/ijcnn.2010.5596811","title":"Region enhanced neural Q-learning for solving model-based POMDPs","display_name":"Region enhanced neural Q-learning for solving model-based POMDPs","publication_year":2010,"publication_date":"2010-07-01","ids":{"openalex":"https://openalex.org/W2129502467","doi":"https://doi.org/10.1109/ijcnn.2010.5596811","mag":"2129502467"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2010.5596811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2010.5596811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2010 International Joint Conference on Neural Networks (IJCNN)","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/A5060596453","display_name":"Marco Wiering","orcid":"https://orcid.org/0000-0003-4331-7537"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Marco A. Wiering","raw_affiliation_strings":["Department of Artificial Intelligence, University of Groningam, Netherlands","Dept. of Artificial Intelligence, University of Groningen, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, University of Groningam, Netherlands","institution_ids":[]},{"raw_affiliation_string":"Dept. of Artificial Intelligence, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057937692","display_name":"Thijs Kooi","orcid":"https://orcid.org/0000-0001-5565-5029"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Thijs Kooi","raw_affiliation_strings":["Department of Artificial Intelligence, University of Groningam, Netherlands","Dept. of Artificial Intelligence, University of Groningen, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, University of Groningam, Netherlands","institution_ids":[]},{"raw_affiliation_string":"Dept. of Artificial Intelligence, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060596453"],"corresponding_institution_ids":["https://openalex.org/I169381384"],"apc_list":null,"apc_paid":null,"fwci":0.4655,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75120443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"27","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9937000274658203,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9937000274658203,"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":0.9936000108718872,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9930999875068665,"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-process","display_name":"Partially observable Markov decision process","score":0.7750638723373413},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7455646395683289},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6714591979980469},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6161065101623535},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.6027756333351135},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5977961421012878},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5264533162117004},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43557512760162354},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.43345892429351807},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.41440096497535706},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.381175696849823},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3409963548183441},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.315540075302124},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22717738151550293},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.17148715257644653},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11095085740089417}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.7750638723373413},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7455646395683289},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6714591979980469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6161065101623535},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6027756333351135},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5977961421012878},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5264533162117004},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43557512760162354},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.43345892429351807},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.41440096497535706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.381175696849823},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3409963548183441},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.315540075302124},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22717738151550293},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.17148715257644653},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11095085740089417},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn.2010.5596811","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2010.5596811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2010 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.719.1452","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.719.1452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ai.rug.nl/%7Emwiering/GROUP/ARTICLES/RENQ.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W20231115","https://openalex.org/W158205031","https://openalex.org/W166862392","https://openalex.org/W1539216098","https://openalex.org/W1557517019","https://openalex.org/W1563317173","https://openalex.org/W1983362322","https://openalex.org/W1997350370","https://openalex.org/W2011418219","https://openalex.org/W2043806097","https://openalex.org/W2065087844","https://openalex.org/W2079188298","https://openalex.org/W2099430963","https://openalex.org/W2107726111","https://openalex.org/W2110962519","https://openalex.org/W2113096211","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2122410182","https://openalex.org/W2123651102","https://openalex.org/W2141559645","https://openalex.org/W2143865185","https://openalex.org/W2144088174","https://openalex.org/W2158907787","https://openalex.org/W2162915993","https://openalex.org/W2168762208","https://openalex.org/W2334782222","https://openalex.org/W2341171179","https://openalex.org/W3011120880","https://openalex.org/W3101822862","https://openalex.org/W3139377883","https://openalex.org/W4214717370","https://openalex.org/W4255985591","https://openalex.org/W4256160650","https://openalex.org/W6674541415","https://openalex.org/W6677050150","https://openalex.org/W6681718981"],"related_works":["https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W1589140671","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W4323315247","https://openalex.org/W131709709"],"abstract_inverted_index":{"To":[0,41],"get":[1],"a":[2,38,62,77],"robot":[3,9,26],"to":[4,11,32,101,111],"perform":[5],"tasks":[6,130],"autonomously,":[7],"the":[8,20,59,74,81,102,142],"has":[10],"plan":[12],"its":[13],"behavior":[14],"and":[15,28,95,113,139],"make":[16],"decisions":[17],"based":[18],"on":[19,125,136],"input":[21],"it":[22],"receives.":[23],"Unfortunately,":[24],"contemporary":[25],"sensors":[27],"actuators":[29],"are":[30,97],"subject":[31],"noise,":[33],"rendering":[34],"optimal":[35],"decision":[36,48],"making":[37],"stochastic":[39],"process.":[40],"model":[42],"this":[43,55],"process,":[44],"partially":[45],"observable":[46],"Markov":[47],"processes":[49],"(POMDPs)":[50],"can":[51],"be":[52],"applied.":[53],"In":[54],"paper":[56],"we":[57],"introduce":[58],"RENQ":[60,84,110,133],"algorithm,":[61],"new":[63],"POMDP":[64],"algorithm":[65],"that":[66,132],"combines":[67],"neural":[68,103],"networks":[69],"for":[70,118],"estimating":[71],"Q-values":[72],"with":[73,91,106],"construction":[75],"of":[76],"spatial":[78],"pyramid":[79],"over":[80],"state":[82],"space.":[83],"essentially":[85],"uses":[86],"region-based":[87],"belief":[88,93],"vectors":[89],"together":[90],"state-based":[92],"vectors,":[94],"these":[96],"used":[98],"as":[99],"inputs":[100],"network":[104],"trained":[105],"Q-learning.":[107],"We":[108],"compare":[109],"Qmdp":[112,140],"Perseus,":[114],"two":[115],"state-of-the-art":[116],"algorithms":[117],"approximately":[119],"solving":[120],"model-based":[121],"POMDPs.":[122],"The":[123],"results":[124],"three":[126],"different":[127],"maze":[128],"navigation":[129],"indicate":[131],"outperforms":[134],"Perseus":[135],"all":[137],"problems":[138],"if":[141],"problem":[143],"becomes":[144],"larger.":[145]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}