{"id":"https://openalex.org/W2106652155","doi":"https://doi.org/10.1109/adprl.2009.4927527","title":"A convergent recursive least squares approximate policy iteration algorithm for multi-dimensional Markov decision process with continuous state and action spaces","display_name":"A convergent recursive least squares approximate policy iteration algorithm for multi-dimensional Markov decision process with continuous state and action spaces","publication_year":2009,"publication_date":"2009-03-01","ids":{"openalex":"https://openalex.org/W2106652155","doi":"https://doi.org/10.1109/adprl.2009.4927527","mag":"2106652155"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2009.4927527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","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/A5101851474","display_name":"Jun Ma","orcid":"https://orcid.org/0000-0002-4551-203X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jun Ma","raw_affiliation_strings":["Department of Operations Research and Financial Engineering, Princeton University, Princeton, NJ, USA","Department of Operations Research and Financial Engineering, Princeton University, New Jersey, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Operations Research and Financial Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Department of Operations Research and Financial Engineering, Princeton University, New Jersey, USA#TAB#","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054833334","display_name":"Warren B. Powell","orcid":"https://orcid.org/0000-0002-4364-7555"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Warren B. Powell","raw_affiliation_strings":["Department of Operations Research and Financial Engineering, Princeton University, Princeton, NJ, USA","Department of Operations Research and Financial Engineering, Princeton University, New Jersey, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Operations Research and Financial Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Department of Operations Research and Financial Engineering, Princeton University, New Jersey, USA#TAB#","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101851474"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":1.3549,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.85020725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9739000201225281,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9722999930381775,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/markov-decision-process","display_name":"Markov decision process","score":0.8829271197319031},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6539250016212463},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5523192286491394},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5278598666191101},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.48535457253456116},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4818495512008667},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47027355432510376},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.45010703802108765},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.44841068983078003},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4363541603088379},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.42215192317962646},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.39863187074661255},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0887480080127716}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8829271197319031},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6539250016212463},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5523192286491394},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5278598666191101},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.48535457253456116},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4818495512008667},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47027355432510376},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45010703802108765},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44841068983078003},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4363541603088379},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.42215192317962646},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.39863187074661255},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0887480080127716},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/adprl.2009.4927527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.150.4938","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.150.4938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.castlelab.princeton.edu/Papers/MaPowell_ConvergentADPalgorithmFeb152009.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.888.5364","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.888.5364","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://castlelab.princeton.edu/Papers/RLS%20policy%20iteration%20convergence%20for%20continuous%20state%20and%20action%20spaces.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W203117010","https://openalex.org/W649399730","https://openalex.org/W1506961945","https://openalex.org/W1529558080","https://openalex.org/W1542118577","https://openalex.org/W1547105496","https://openalex.org/W1550698229","https://openalex.org/W1552132860","https://openalex.org/W1553308207","https://openalex.org/W1576452626","https://openalex.org/W1597926580","https://openalex.org/W1601081659","https://openalex.org/W1616818660","https://openalex.org/W1646707810","https://openalex.org/W1995713768","https://openalex.org/W1997696513","https://openalex.org/W2027184806","https://openalex.org/W2040766536","https://openalex.org/W2053323451","https://openalex.org/W2056858451","https://openalex.org/W2072931156","https://openalex.org/W2104335146","https://openalex.org/W2104753538","https://openalex.org/W2105336508","https://openalex.org/W2115558605","https://openalex.org/W2121832485","https://openalex.org/W2121863487","https://openalex.org/W2122689259","https://openalex.org/W2124599560","https://openalex.org/W2125074935","https://openalex.org/W2126025075","https://openalex.org/W2135231381","https://openalex.org/W2137466452","https://openalex.org/W2139418546","https://openalex.org/W2149148771","https://openalex.org/W2151416233","https://openalex.org/W2156974606","https://openalex.org/W2169982856","https://openalex.org/W2334782222","https://openalex.org/W2487144912","https://openalex.org/W2792296590","https://openalex.org/W4214717370","https://openalex.org/W4230447275","https://openalex.org/W4242606736","https://openalex.org/W4245296547","https://openalex.org/W4246808543","https://openalex.org/W4285719527","https://openalex.org/W6630598529","https://openalex.org/W6675698164","https://openalex.org/W6678518843","https://openalex.org/W6678545291","https://openalex.org/W6680602176","https://openalex.org/W6682074005","https://openalex.org/W7037607071"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W2016648086","https://openalex.org/W3105579180","https://openalex.org/W2156021013","https://openalex.org/W4399157305","https://openalex.org/W4281791088"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5],"recursive":[6],"least":[7],"squares":[8],"approximate":[9,38,58],"policy":[10,35,39,59],"iteration":[11,40],"(RLSAPI)":[12],"algorithm":[13,41],"for":[14],"infinite-horizon":[15],"multi-dimensional":[16],"Markov":[17],"decision":[18],"process":[19],"in":[20,45],"continuous":[21],"state":[22],"and":[23,34],"action":[24],"spaces.":[25],"Under":[26],"certain":[27],"problem":[28],"structure":[29],"assumptions":[30],"on":[31],"value":[32,60,65],"functions":[33],"spaces,":[36],"the":[37,46,52,57,63],"is":[42,49],"provably":[43],"convergent":[44],"mean.":[47],"That":[48],"to":[50,68],"say":[51],"mean":[53],"absolute":[54],"deviation":[55],"of":[56],"function":[61,66],"from":[62],"optimal":[64],"goes":[67],"zero":[69],"as":[70],"successive":[71],"approximation":[72],"improves.":[73]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}