{"id":"https://openalex.org/W2086608109","doi":"https://doi.org/10.1109/tnn.2011.2168422","title":"Hierarchical Approximate Policy Iteration With Binary-Tree State Space Decomposition","display_name":"Hierarchical Approximate Policy Iteration With Binary-Tree State Space Decomposition","publication_year":2011,"publication_date":"2011-10-12","ids":{"openalex":"https://openalex.org/W2086608109","doi":"https://doi.org/10.1109/tnn.2011.2168422","mag":"2086608109","pmid":"https://pubmed.ncbi.nlm.nih.gov/21990333"},"language":"en","primary_location":{"id":"doi:10.1109/tnn.2011.2168422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnn.2011.2168422","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/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 Technology, Changsha 410073, China. xinxu@nudt.edu.cn","Coll. of Mechatron. & Autom., Nat. Univ. of Defense Tech, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha 410073, China. xinxu@nudt.edu.cn","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Coll. of Mechatron. & Autom., Nat. Univ. of Defense Tech, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100623405","display_name":"Chunming Liu","orcid":"https://orcid.org/0000-0002-0564-4476"},"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":"Chunming Liu","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","Coll. of Mechatron. & Autom., Nat. Univ. of Defense Tech, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Coll. of Mechatron. & Autom., Nat. Univ. of Defense Tech, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029827598","display_name":"Simon X. Yang","orcid":"https://orcid.org/0000-0002-6888-7993"},"institutions":[{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"S. X. Yang","raw_affiliation_strings":["School of Engineering, University of Guelph, Guelph, ONT, Canada","School of Engineering University of Guelph  Guelph ON Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, University of Guelph, Guelph, ONT, Canada","institution_ids":["https://openalex.org/I79817857"]},{"raw_affiliation_string":"School of Engineering University of Guelph  Guelph ON Canada","institution_ids":["https://openalex.org/I79817857"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071074935","display_name":"Dewen Hu","orcid":"https://orcid.org/0000-0001-7357-0053"},"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":"Dewen Hu","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","Coll. of Mechatron. & Autom., Nat. Univ. of Defense Tech, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Coll. of Mechatron. & Autom., Nat. Univ. of Defense Tech, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.1962,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.97439927,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"22","issue":"12","first_page":"1863","last_page":"1877"},"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":0.9966999888420105,"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":0.9711999893188477,"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":0.7290814518928528},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7192829251289368},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6577150821685791},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5393298864364624},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.49045297503471375},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4727914035320282},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4372452199459076},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32923102378845215},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3255201280117035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30252230167388916},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23249846696853638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7290814518928528},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7192829251289368},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6577150821685791},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5393298864364624},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.49045297503471375},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4727914035320282},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4372452199459076},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32923102378845215},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3255201280117035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30252230167388916},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23249846696853638},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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":"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":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tnn.2011.2168422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnn.2011.2168422","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:21990333","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21990333","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":[{"score":0.6399999856948853,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1492518272","https://openalex.org/W1540839255","https://openalex.org/W1574700590","https://openalex.org/W1576452626","https://openalex.org/W1583380718","https://openalex.org/W1584456573","https://openalex.org/W1585546214","https://openalex.org/W1592847719","https://openalex.org/W1730555343","https://openalex.org/W1754881896","https://openalex.org/W1981276685","https://openalex.org/W1984666348","https://openalex.org/W2041367235","https://openalex.org/W2043806097","https://openalex.org/W2050838777","https://openalex.org/W2089561656","https://openalex.org/W2101881799","https://openalex.org/W2104753538","https://openalex.org/W2105004188","https://openalex.org/W2107628283","https://openalex.org/W2108734173","https://openalex.org/W2109301240","https://openalex.org/W2109910161","https://openalex.org/W2117355432","https://openalex.org/W2118556122","https://openalex.org/W2120346334","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2128812357","https://openalex.org/W2132351269","https://openalex.org/W2133120480","https://openalex.org/W2134882417","https://openalex.org/W2137092694","https://openalex.org/W2139418546","https://openalex.org/W2139984767","https://openalex.org/W2143496582","https://openalex.org/W2148603752","https://openalex.org/W2150923691","https://openalex.org/W2153290280","https://openalex.org/W2156737235","https://openalex.org/W2158548602","https://openalex.org/W2159543578","https://openalex.org/W2341171179","https://openalex.org/W2492794003","https://openalex.org/W2596585349","https://openalex.org/W2612972698","https://openalex.org/W3103182070","https://openalex.org/W3139474403","https://openalex.org/W4214717370","https://openalex.org/W4242606736","https://openalex.org/W4285719527","https://openalex.org/W6634919779","https://openalex.org/W6637597983","https://openalex.org/W6637806891","https://openalex.org/W6672734911","https://openalex.org/W6677737365","https://openalex.org/W6677949083","https://openalex.org/W6680148360","https://openalex.org/W6681398095","https://openalex.org/W6682443896","https://openalex.org/W6786397483"],"related_works":["https://openalex.org/W1985560493","https://openalex.org/W2482498454","https://openalex.org/W1556532828","https://openalex.org/W4286713570","https://openalex.org/W1574991376","https://openalex.org/W3201878770","https://openalex.org/W2937181779","https://openalex.org/W4384616108","https://openalex.org/W4362647313","https://openalex.org/W4287081775"],"abstract_inverted_index":{"In":[0,84],"recent":[1],"years,":[2],"approximate":[3,127],"policy":[4,17,177,183],"iteration":[5,18],"(API)":[6],"has":[7],"attracted":[8],"increasing":[9],"attention":[10],"in":[11,69,92,190],"reinforcement":[12],"learning":[13,81,148,195],"(RL),":[14],"e.g.,":[15],"least-squares":[16],"(LSPI)":[19],"and":[20,162,224,241],"its":[21],"kernelized":[22],"version,":[23],"the":[24,85,93,97,111,123,147,168,174,181,191,210,213,217,227],"kernel-based":[25],"LSPI":[26,240],"algorithm.":[27],"However,":[28],"it":[29],"remains":[30],"difficult":[31],"for":[32,39,67,220],"API":[33,59,118,157,188,236],"algorithms":[34,119,158],"to":[35,109,126,208],"obtain":[36],"near-optimal":[37,152,182,232],"policies":[38,130,153,233],"Markov":[40],"decision":[41],"processes":[42],"(MDPs)":[43],"with":[44,62,159],"large":[45],"or":[46],"continuous":[47],"state":[48,64,94,113],"spaces.":[49],"To":[50],"address":[51],"this":[52,54],"problem,":[53],"paper":[55],"presents":[56],"a":[57,70,100,139,186,202],"hierarchical":[58],"(HAPI)":[60],"method":[61],"binary-tree":[63,112,140],"space":[65,95,114],"decomposition":[66,102,115],"RL":[68],"class":[71],"of":[72,96,104,131,142,167,171,201,212],"absorbing":[73,143],"MDPs,":[74],"which":[75],"can":[76],"be":[77],"formulated":[78],"as":[79,239],"time-optimal":[80],"control":[82,196,200],"tasks.":[83],"proposed":[86,228],"method,":[87],"after":[88],"collecting":[89],"samples":[90],"adaptively":[91],"original":[98,134,192],"MDP,":[99],"learning-based":[101],"strategy":[103],"sample":[105,124,225],"sets":[106],"was":[107,136],"designed":[108],"implement":[110],"process.":[116],"Then,":[117],"were":[120,154,206],"used":[121],"on":[122],"subsets":[125],"local":[128,151,172],"optimal":[129],"sub-MDPs.":[132],"The":[133],"MDP":[135],"decomposed":[137],"into":[138],"structure":[141],"sub-MDPs,":[144],"constructed":[145],"during":[146],"process,":[149],"thus,":[150],"approximated":[155],"by":[156,185],"reduced":[160],"complexity":[161],"higher":[163],"precision.":[164],"Furthermore,":[165],"because":[166],"improved":[169],"quality":[170],"policies,":[173],"combined":[175],"global":[176],"performed":[178],"better":[179,231],"than":[180,234],"obtained":[184,230],"single":[187],"algorithm":[189],"MDP.":[193],"Three":[194],"problems,":[197],"including":[198],"path-tracking":[199],"real":[203],"mobile":[204],"robot,":[205],"studied":[207],"evaluate":[209],"performance":[211],"HAPI":[214,229],"method.":[215],"With":[216],"same":[218],"setting":[219],"basis":[221],"function":[222],"selection":[223],"collection,":[226],"previous":[235],"methods":[237],"such":[238],"KLSPI.":[242]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":9}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}