{"id":"https://openalex.org/W1984666348","doi":"https://doi.org/10.1109/tnn.2010.2050334","title":"Approximate Robust Policy Iteration Using Multilayer Perceptron Neural Networks for Discounted Infinite-Horizon Markov Decision Processes With Uncertain Correlated Transition Matrices","display_name":"Approximate Robust Policy Iteration Using Multilayer Perceptron Neural Networks for Discounted Infinite-Horizon Markov Decision Processes With Uncertain Correlated Transition Matrices","publication_year":2010,"publication_date":"2010-07-08","ids":{"openalex":"https://openalex.org/W1984666348","doi":"https://doi.org/10.1109/tnn.2010.2050334","mag":"1984666348","pmid":"https://pubmed.ncbi.nlm.nih.gov/20601311"},"language":"en","primary_location":{"id":"doi:10.1109/tnn.2010.2050334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnn.2010.2050334","pdf_url":null,"source":{"id":"https://openalex.org/S42080949","display_name":"IEEE Transactions on Neural Networks","issn_l":"1045-9227","issn":["1045-9227","1941-0093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100705575","display_name":"Baohua Li","orcid":"https://orcid.org/0000-0002-4540-0441"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baohua Li","raw_affiliation_strings":["Arkansas Institute for Nanomaterial Science and Engineering, University of Arkansas, Fayetteville, AR 72701, USA. Baohua.Li@asu.edu","Arkansas Inst. for Nanomater. Sci. & Eng., Univ. of Arkansas, Fayetteville, AR, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arkansas Institute for Nanomaterial Science and Engineering, University of Arkansas, Fayetteville, AR 72701, USA. Baohua.Li@asu.edu","institution_ids":["https://openalex.org/I78715868"]},{"raw_affiliation_string":"Arkansas Inst. for Nanomater. Sci. & Eng., Univ. of Arkansas, Fayetteville, AR, USA","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085653399","display_name":"Jennie Si","orcid":"https://orcid.org/0000-0002-0374-7404"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J Si","raw_affiliation_strings":["Department of Electrical Engineering, Arizona State University, Tempe, AZ, USA","Dept. of Electr. Eng.. Arizona State Univ., Tempe, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Dept. of Electr. Eng.. Arizona State Univ., Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.263,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.92042435,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"21","issue":"8","first_page":"1270","last_page":"1280"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9994000196456909,"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/T10603","display_name":"Smart Grid Energy Management","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/markov-decision-process","display_name":"Markov decision process","score":0.8329725861549377},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6700124740600586},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5731582045555115},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5654201507568359},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5064660310745239},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5026342868804932},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4730880856513977},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.46796828508377075},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4603988230228424},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42010581493377686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15355175733566284}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8329725861549377},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6700124740600586},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5731582045555115},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5654201507568359},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5064660310745239},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5026342868804932},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4730880856513977},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.46796828508377075},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4603988230228424},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42010581493377686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15355175733566284},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003661","descriptor_name":"Decision Support Techniques","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003661","descriptor_name":"Decision Support Techniques","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003661","descriptor_name":"Decision Support Techniques","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003662","descriptor_name":"Decision Theory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003662","descriptor_name":"Decision Theory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003662","descriptor_name":"Decision Theory","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D055641","descriptor_name":"Mathematical Concepts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055641","descriptor_name":"Mathematical Concepts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055641","descriptor_name":"Mathematical Concepts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tnn.2010.2050334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnn.2010.2050334","pdf_url":null,"source":{"id":"https://openalex.org/S42080949","display_name":"IEEE Transactions on Neural Networks","issn_l":"1045-9227","issn":["1045-9227","1941-0093"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks","raw_type":"journal-article"},{"id":"pmid:20601311","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20601311","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1497451517","https://openalex.org/W1497711688","https://openalex.org/W1515852644","https://openalex.org/W1517613402","https://openalex.org/W1854776945","https://openalex.org/W1965878388","https://openalex.org/W1988217924","https://openalex.org/W1992821128","https://openalex.org/W2016309114","https://openalex.org/W2036931518","https://openalex.org/W2058811924","https://openalex.org/W2069045459","https://openalex.org/W2102773314","https://openalex.org/W2119567691","https://openalex.org/W2124776405","https://openalex.org/W2127348787","https://openalex.org/W2296319761","https://openalex.org/W2334782222","https://openalex.org/W4250589301","https://openalex.org/W4255242490","https://openalex.org/W6631055690"],"related_works":["https://openalex.org/W4389475841","https://openalex.org/W4241327272","https://openalex.org/W2120406836","https://openalex.org/W1996214847","https://openalex.org/W2903299703","https://openalex.org/W4211224558","https://openalex.org/W2117282672","https://openalex.org/W1672382258","https://openalex.org/W2119790124","https://openalex.org/W4281791088"],"abstract_inverted_index":{"We":[0,120],"study":[1],"finite-state,":[2],"finite-action,":[3],"discounted":[4],"infinite-horizon":[5],"Markov":[6],"decision":[7],"processes":[8],"with":[9],"uncertain":[10],"correlated":[11],"transition":[12],"matrices":[13],"in":[14,63,76],"deterministic":[15],"policy":[16,45,75],"spaces.":[17],"Existing":[18],"robust":[19,39,44],"dynamic":[20],"programming":[21],"methods":[22],"cannot":[23],"be":[24,93],"extended":[25],"to":[26,69,95,124],"solving":[27],"this":[28,34,97],"class":[29,98],"of":[30,99],"general":[31],"problems.":[32,100],"In":[33,80],"paper,":[35],"based":[36,105],"on":[37,106],"a":[38,48,70,77,88,102,117],"optimality":[40],"criterion,":[41],"an":[42,135],"approximate":[43],"iteration":[46],"using":[47],"multilayer":[49],"perceptron":[50],"neural":[51],"network":[52],"is":[53,56,116,130],"proposed.":[54],"It":[55],"proven":[57],"that":[58,85,126],"the":[59,113],"proposed":[60,108,128],"algorithm":[61,129],"converges":[62,68],"finite":[64],"iterations,":[65],"and":[66],"it":[67],"stationary":[71],"optimal":[72],"or":[73],"near-optimal":[74],"probability":[78],"sense.":[79],"addition,":[81],"we":[82],"point":[83],"out":[84],"sometimes":[86],"even":[87],"direct":[89,103],"enumeration":[90,104,136],"may":[91],"not":[92],"applicable":[94],"addressing":[96],"However,":[101],"our":[107,127],"maximum":[109],"value":[110],"approximation":[111],"over":[112],"parameter":[114],"space":[115],"feasible":[118],"approach.":[119],"provide":[121],"further":[122],"analysis":[123],"show":[125],"more":[131],"efficient":[132],"than":[133],"such":[134],"method":[137],"for":[138],"various":[139],"scenarios.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}