{"id":"https://openalex.org/W2153227067","doi":"https://doi.org/10.1109/ijcnn.2007.4371274","title":"Approximate Robust Policy Iteration for Discounted Infinite-Horizon Markov Decision Processes with Uncertain Stationary Parametric Transition Matrices","display_name":"Approximate Robust Policy Iteration for Discounted Infinite-Horizon Markov Decision Processes with Uncertain Stationary Parametric Transition Matrices","publication_year":2007,"publication_date":"2007-08-01","ids":{"openalex":"https://openalex.org/W2153227067","doi":"https://doi.org/10.1109/ijcnn.2007.4371274","mag":"2153227067"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2007.4371274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2007.4371274","pdf_url":null,"source":{"id":"https://openalex.org/S4210195743","display_name":"IEEE International Conference on Neural Networks/IEEE ... International Conference on Neural Networks","issn_l":"1098-7576","issn":["1098-7576","1558-3902"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 International Joint Conference on Neural Networks","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/A5100705575","display_name":"Baohua Li","orcid":"https://orcid.org/0000-0002-4540-0441"},"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":true,"raw_author_name":"Baohua Li","raw_affiliation_strings":["Department of Electrical Engineering, Arizona State University, Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"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":"Jennie Si","raw_affiliation_strings":["Department of Electrical Engineering, Arizona State University, Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100705575"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23404255,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"50","issue":null,"first_page":"2052","last_page":"2057"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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/T11236","display_name":"Control Systems and Identification","score":0.9833999872207642,"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/markov-decision-process","display_name":"Markov decision process","score":0.7884230613708496},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5908561944961548},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5215998888015747},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5098718404769897},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4952186644077301},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.49463221430778503},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4928276836872101},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.464724600315094},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4503154754638672},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.44543319940567017},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.437216579914093}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7884230613708496},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5908561944961548},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5215998888015747},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5098718404769897},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4952186644077301},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.49463221430778503},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4928276836872101},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.464724600315094},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4503154754638672},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.44543319940567017},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.437216579914093},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2007.4371274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2007.4371274","pdf_url":null,"source":{"id":"https://openalex.org/S4210195743","display_name":"IEEE International Conference on Neural Networks/IEEE ... International Conference on Neural Networks","issn_l":"1098-7576","issn":["1098-7576","1558-3902"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 International Joint Conference on Neural Networks","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W92805021","https://openalex.org/W1497451517","https://openalex.org/W1515852644","https://openalex.org/W1576452626","https://openalex.org/W1854776945","https://openalex.org/W1931354637","https://openalex.org/W1965878388","https://openalex.org/W1988217924","https://openalex.org/W2016309114","https://openalex.org/W2036931518","https://openalex.org/W2069045459","https://openalex.org/W2101167844","https://openalex.org/W2102773314","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2124776405","https://openalex.org/W2127348787","https://openalex.org/W2147680262","https://openalex.org/W2285257517","https://openalex.org/W2334782222","https://openalex.org/W3213472335","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W6603762378","https://openalex.org/W6630918991","https://openalex.org/W6654355633","https://openalex.org/W6678851513","https://openalex.org/W6804409665"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W4308702637","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W1859185863","https://openalex.org/W2016648086","https://openalex.org/W2156021013","https://openalex.org/W2807018115"],"abstract_inverted_index":{"We":[0],"consider":[1],"Markov":[2],"decision":[3],"processes":[4],"with":[5,25,110,135],"finite":[6,8],"states,":[7],"actions,":[9],"and":[10,54,95,122],"discounted":[11],"infinite-horizon":[12],"cost":[13],"in":[14,30,51,139,160],"the":[15,45,59,72,103,128,152,161],"deterministic":[16,162],"policy":[17,68,105,130,163],"space.":[18,164],"State":[19],"transition":[20,31],"matrices":[21,32],"are":[22,70,77,155],"uncertain":[23],"but":[24],"stationary":[26,117,145,153],"parameterization.":[27],"The":[28,87],"uncertainty":[29],"signifies":[33],"realistic":[34],"considerations":[35],"that":[36,102,124],"an":[37,82],"accurate":[38],"system":[39],"model":[40,55],"is":[41,100],"not":[42],"available":[43],"for":[44],"controller":[46],"design":[47],"due":[48],"to":[49,79,115,143,157],"limitations":[50],"estimation":[52],"methods":[53],"deficiencies.":[56],"Based":[57],"on":[58,108,133],"quadratic":[60],"total":[61],"value":[62],"function":[63],"formulation,":[64],"two":[65,88],"approximate":[66],"robust":[67,104,129],"iterations":[69],"developed,":[71],"performance":[73],"errors":[74],"of":[75,92],"which":[76],"guaranteed":[78,156],"be":[80,158],"within":[81],"arbitrarily":[83],"small":[84],"error":[85],"bound.":[86],"approximations":[89],"make":[90],"use":[91],"iterative":[93,111],"aggregation":[94,112],"multilayer":[96,136],"perceptron,":[97],"respectively.":[98],"It":[99],"proved":[101],"iteration":[106,131],"based":[107,132],"approximation":[109,134],"converges":[113,138],"surely":[114],"a":[116,140,144],"optimal":[118],"or":[119],"near-optimal":[120,146,159],"policy,":[121],"also":[123],"under":[125,149],"some":[126,150],"conditions":[127],"perceptron":[137],"probability":[141],"sense":[142],"policy.":[147],"Furthermore,":[148],"assumptions,":[151],"solutions":[154]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}