{"id":"https://openalex.org/W1497402429","doi":"https://doi.org/10.1007/978-3-642-36669-7_89","title":"A Hierarchical Representation Policy Iteration Algorithm for Reinforcement Learning","display_name":"A Hierarchical Representation Policy Iteration Algorithm for Reinforcement Learning","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W1497402429","doi":"https://doi.org/10.1007/978-3-642-36669-7_89","mag":"1497402429"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-36669-7_89","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-36669-7_89","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5100370436","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0002-3737-4175"},"institutions":[{"id":"https://openalex.org/I4210088839","display_name":"People 's Liberation Army 451 Hospital","ror":"https://ror.org/007w9h140","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210088839"]},{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jian Wang","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Tech., Changsha, 410073, P.R. China","Xi\u2019an Air Force Military Representative Office, China"],"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Tech., Changsha, 410073, P.R. China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Xi\u2019an Air Force Military Representative Office, China","institution_ids":["https://openalex.org/I4210088839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057599028","display_name":"Lei Zuo","orcid":"https://orcid.org/0000-0002-9938-7449"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zuo","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Tech., Changsha, 410073, P.R. China"],"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Tech., Changsha, 410073, P.R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100696824","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0002-4316-932X"},"institutions":[{"id":"https://openalex.org/I4210088839","display_name":"People 's Liberation Army 451 Hospital","ror":"https://ror.org/007w9h140","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210088839"]},{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wang","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Tech., Changsha, 410073, P.R. China","Xi\u2019an Air Force Military Representative Office, China"],"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Tech., Changsha, 410073, P.R. China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Xi\u2019an Air Force Military Representative Office, China","institution_ids":["https://openalex.org/I4210088839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Tech., Changsha, 410073, P.R. China"],"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Tech., Changsha, 410073, P.R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100371573","display_name":"Chun Li","orcid":"https://orcid.org/0000-0003-2311-3422"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Li","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Tech., Changsha, 410073, P.R. China"],"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Tech., Changsha, 410073, P.R. China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100370436"],"corresponding_institution_ids":["https://openalex.org/I170215575","https://openalex.org/I4210088839"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.6789,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71695539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"735","last_page":"742"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9937999844551086,"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/T14011","display_name":"Elevator Systems and Control","score":0.982200026512146,"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/computer-science","display_name":"Computer science","score":0.7190496921539307},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7001093029975891},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.640997588634491},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6289873123168945},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5991310477256775},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.538786768913269},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.509425938129425},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4520242214202881},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.44972020387649536},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44503721594810486},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4209336042404175},{"id":"https://openalex.org/keywords/binary-tree","display_name":"Binary tree","score":0.41292843222618103},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4117826819419861},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2048482894897461},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19946005940437317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7190496921539307},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7001093029975891},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.640997588634491},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6289873123168945},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5991310477256775},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.538786768913269},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.509425938129425},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4520242214202881},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.44972020387649536},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44503721594810486},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4209336042404175},{"id":"https://openalex.org/C197855036","wikidata":"https://www.wikidata.org/wiki/Q380172","display_name":"Binary tree","level":2,"score":0.41292843222618103},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4117826819419861},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2048482894897461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19946005940437317},{"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-642-36669-7_89","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-36669-7_89","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"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":15,"referenced_works":["https://openalex.org/W146900863","https://openalex.org/W1515851193","https://openalex.org/W1592847719","https://openalex.org/W2086608109","https://openalex.org/W2089561656","https://openalex.org/W2109910161","https://openalex.org/W2118556122","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2134882417","https://openalex.org/W2161795906","https://openalex.org/W3202461034","https://openalex.org/W4214717370","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W3099153698","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W2902549273"],"abstract_inverted_index":null,"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}