{"id":"https://openalex.org/W4406728069","doi":"https://doi.org/10.1109/tsmc.2025.3525473","title":"Visionary Policy Iteration for Continuous Control","display_name":"Visionary Policy Iteration for Continuous Control","publication_year":2025,"publication_date":"2025-01-22","ids":{"openalex":"https://openalex.org/W4406728069","doi":"https://doi.org/10.1109/tsmc.2025.3525473"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2025.3525473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3525473","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-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/A5002412202","display_name":"Botao Dong","orcid":"https://orcid.org/0000-0002-2026-6856"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Botao Dong","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2026-6856","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085372626","display_name":"Longyang Huang","orcid":"https://orcid.org/0000-0001-5123-5043"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longyang Huang","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5123-5043","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016503021","display_name":"Xiwen Ma","orcid":"https://orcid.org/0000-0001-9212-3523"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiwen Ma","raw_affiliation_strings":["School of Oceanography, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9212-3523","affiliations":[{"raw_affiliation_string":"School of Oceanography, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019419996","display_name":"Hongtian Chen","orcid":"https://orcid.org/0000-0002-8600-9668"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtian Chen","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8600-9668","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100414775","display_name":"Weidong Zhang","orcid":"https://orcid.org/0000-0002-4700-1276"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Zhang","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4700-1276","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":4.5766,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.93529924,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"55","issue":"4","first_page":"2707","last_page":"2720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.2092999964952469,"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"}},"topics":[{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.2092999964952469,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.18369999527931213,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/control","display_name":"Control (management)","score":0.51790851354599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3761608898639679},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09362360835075378}],"concepts":[{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.51790851354599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3761608898639679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09362360835075378}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2025.3525473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3525473","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G149237651","display_name":null,"funder_award_id":"22015810300","funder_id":"https://openalex.org/F4320336736","funder_display_name":"Chengdu Science and Technology Program"},{"id":"https://openalex.org/G1852921944","display_name":null,"funder_award_id":"2022ZD0119903","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2260626412","display_name":null,"funder_award_id":"U24A20260","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5721963804","display_name":null,"funder_award_id":"U2141234","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336736","display_name":"Chengdu Science and Technology Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1677182931","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2583232117","https://openalex.org/W2999863957","https://openalex.org/W3047221759","https://openalex.org/W3127198723","https://openalex.org/W3154632874","https://openalex.org/W3165885159","https://openalex.org/W3170872007","https://openalex.org/W3188220908","https://openalex.org/W4226257065","https://openalex.org/W4283789523","https://openalex.org/W4285411788","https://openalex.org/W4295308578","https://openalex.org/W4310467047","https://openalex.org/W4311486598","https://openalex.org/W4375796951","https://openalex.org/W4377298394","https://openalex.org/W4382239134","https://openalex.org/W4384499218","https://openalex.org/W4385338914","https://openalex.org/W4386883060","https://openalex.org/W4387415195","https://openalex.org/W4388052800","https://openalex.org/W4388543828","https://openalex.org/W4390481125","https://openalex.org/W4391759535","https://openalex.org/W4395680426","https://openalex.org/W4396542660","https://openalex.org/W4396909955","https://openalex.org/W4399562950","https://openalex.org/W4399666158","https://openalex.org/W4401024156","https://openalex.org/W6684921986","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6780559895","https://openalex.org/W6784938585","https://openalex.org/W6791110673","https://openalex.org/W6841549819","https://openalex.org/W6845850219","https://openalex.org/W6853445487"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0,20],"this":[1],"article,":[2],"a":[3,22,61,66,143],"novel":[4],"visionary":[5,23,46,80,105,144],"policy":[6,91,94,118,139],"iteration":[7],"(VPI)":[8],"framework":[9,132],"is":[10,25,86,112,148,154],"proposed":[11,45,104],"to":[12,37,124],"address":[13],"the":[14,29,33,38,41,44,54,79,83,90,103,116,125,130,134,187,206],"continuous-action":[15,158],"reinforcement":[16],"learning":[17],"(RL)":[18],"tasks.":[19],"VPI,":[21],"Q-function":[24,47,81,85,197],"constructed":[26],"by":[27],"incorporating":[28],"successor":[30,42],"state":[31,51],"into":[32],"standard":[34,84],"Q-function.":[35,106],"Due":[36],"introduction":[39],"of":[40,72,152,169,208],"state,":[43],"captures":[48],"information":[49],"about":[50],"transitions":[52],"within":[53],"Markov":[55],"decision":[56],"process":[57],"(MDP),":[58],"thereby":[59,204],"providing":[60],"forward-looking":[62],"perspective":[63],"that":[64,115,173,191],"enables":[65],"more":[67,177],"accurate":[68],"and":[69,82,93,163,200],"foresighted":[70],"evaluation":[71,92,151],"potential":[73],"action":[74],"outcomes.":[75],"The":[76,107,150,167],"relationship":[77],"between":[78],"analyzed.":[87],"Subsequently,":[88],"both":[89],"improvement":[95],"rules":[96],"in":[97,120],"VPI":[98,111,121,131,192],"are":[99],"designed":[100],"based":[101],"on":[102,156],"convergence":[108],"proof":[109],"for":[110],"provided,":[113],"ensuring":[114],"iterative":[117],"sequence":[119],"will":[122],"converge":[123],"optimal":[126],"policy.":[127],"By":[128],"combining":[129],"with":[133],"twin":[135],"delayed":[136],"deep":[137],"deterministic":[138],"gradient":[140],"(TD3)":[141],"algorithm,":[142],"TD3":[145],"(VTD3)":[146],"algorithm":[147],"developed.":[149],"VTD3":[153,174],"performed":[155],"multiple":[157],"control":[159],"tasks":[160],"from":[161],"Mujoco":[162],"OpenAI":[164],"Gym":[165],"platforms.":[166],"results":[168,189],"comparative":[170],"experiments":[171],"demonstrate":[172],"can":[175],"achieve":[176],"competitive":[178],"performance":[179,207],"than":[180],"other":[181],"state-of-the-art":[182],"(SOTA)":[183],"RL":[184,210],"approaches.":[185],"Additionally,":[186],"experimental":[188],"indicate":[190],"enhances":[193],"decision-making":[194],"capability,":[195],"reduces":[196],"estimation":[198],"bias,":[199],"improves":[201],"sample":[202],"efficiency,":[203],"boosting":[205],"existing":[209],"algorithms.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}