{"id":"https://openalex.org/W7124214543","doi":"https://doi.org/10.1109/icpads67057.2025.11323113","title":"An Adaptive Dynamic Programming Algorithm with Fast Policy Iteration for Optimal Control of Discrete-Time Nonlinear Systems","display_name":"An Adaptive Dynamic Programming Algorithm with Fast Policy Iteration for Optimal Control of Discrete-Time Nonlinear Systems","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124214543","doi":"https://doi.org/10.1109/icpads67057.2025.11323113"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11323113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","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/A5123005388","display_name":"Taotao Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Taotao Wu","raw_affiliation_strings":["School of Computer Engineering, Jiangsu Ocean University,Lianyungang,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Jiangsu Ocean University,Lianyungang,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123048159","display_name":"Bowen Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bowen Yao","raw_affiliation_strings":["School of Computer Engineering, Jiangsu Ocean University,Lianyungang,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Jiangsu Ocean University,Lianyungang,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123016058","display_name":"Heng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng Zhang","raw_affiliation_strings":["School of Computer Engineering, Jiangsu Ocean University,Lianyungang,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Jiangsu Ocean University,Lianyungang,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5123005388"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.77083333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9983999729156494,"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":0.9983999729156494,"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":0.00039999998989515007,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":9.999999747378752e-05,"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/optimal-control","display_name":"Optimal control","score":0.6990000009536743},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6538000106811523},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5497000217437744},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5428000092506409},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5083000063896179},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4909000098705292},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.46389999985694885},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.40400001406669617},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4009000062942505}],"concepts":[{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6990000009536743},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6538000106811523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5687999725341797},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.555899977684021},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5497000217437744},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5428000092506409},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5083000063896179},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4909000098705292},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.46389999985694885},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.40400001406669617},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39899998903274536},{"id":"https://openalex.org/C92292787","wikidata":"https://www.wikidata.org/wiki/Q5275342","display_name":"Differential dynamic programming","level":3,"score":0.37869998812675476},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.34880000352859497},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3249000012874603},{"id":"https://openalex.org/C60810621","wikidata":"https://www.wikidata.org/wiki/Q2333568","display_name":"Optimal substructure","level":3,"score":0.3174999952316284},{"id":"https://openalex.org/C115527620","wikidata":"https://www.wikidata.org/wiki/Q769909","display_name":"Nonlinear programming","level":3,"score":0.30970001220703125},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.29899999499320984},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.27410000562667847},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C2776003309","wikidata":"https://www.wikidata.org/wiki/Q1988072","display_name":"Adaptive algorithm","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11323113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7555255889892578,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W92805021","https://openalex.org/W2013184330","https://openalex.org/W2048687352","https://openalex.org/W2061749308","https://openalex.org/W2089762101","https://openalex.org/W2108286682","https://openalex.org/W2120249358","https://openalex.org/W2136064843","https://openalex.org/W2160561608","https://openalex.org/W2189990206","https://openalex.org/W2490234001","https://openalex.org/W2559988195","https://openalex.org/W2625056686","https://openalex.org/W2992020006","https://openalex.org/W3114263192","https://openalex.org/W3135195117","https://openalex.org/W3172934943","https://openalex.org/W4210548557","https://openalex.org/W4214717370","https://openalex.org/W4379116593","https://openalex.org/W4388579564","https://openalex.org/W4402496391","https://openalex.org/W4409906155","https://openalex.org/W4410915768","https://openalex.org/W4413344184"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"addresses":[2],"the":[3,27,31,58,65,80,90,98,107,117,122],"optimal":[4,32],"control":[5,33],"problem":[6],"for":[7],"discrete-time":[8],"nonlinear":[9],"systems":[10],"with":[11,106],"fixed":[12],"initial":[13],"state.":[14],"A":[15],"fast":[16],"policy":[17],"iteration":[18],"<tex":[19],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[20],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$(\\text{PI})$</tex>":[21],"algorithm":[22,55],"is":[23,86],"developed":[24],"to":[25,88],"compute":[26],"numerical":[28],"solution":[29],"of":[30,53,74,121],"law":[34],"based":[35],"on":[36],"adaptive":[37],"dynamic":[38,41,66],"programming,":[39,42],"where":[40],"artificial":[43],"neural":[44],"network":[45],"and":[46,76,93,110,119],"reinforcement":[47],"learning":[48],"are":[49,84],"used.":[50],"The":[51],"highlight":[52],"this":[54],"lies":[56],"in":[57],"fact":[59],"that":[60],"during":[61],"each":[62],"updating":[63],"iteration,":[64],"sparse":[67],"sampling,":[68,96],"i.e.,":[69],"only":[70],"a":[71],"small":[72],"number":[73],"key":[75],"sensitive":[77],"points":[78],"along":[79],"iterative":[81],"suboptimal":[82],"trajectory":[83],"sampled,":[85],"used":[87],"replace":[89],"traditional":[91],"global":[92,109],"local":[94,111],"spatial":[95],"thus":[97],"computational":[99],"burden":[100],"can":[101],"be":[102],"greatly":[103],"relaxed":[104],"compared":[105],"previous":[108],"PI":[112],"algorithms.":[113],"Numerical":[114],"experiments":[115],"demonstrate":[116],"effectiveness":[118],"rapidity":[120],"proposed":[123],"algorithm.":[124]},"counts_by_year":[],"updated_date":"2026-01-16T23:16:36.188383","created_date":"2026-01-15T00:00:00"}