{"id":"https://openalex.org/W7123359108","doi":"https://doi.org/10.1109/cdc57313.2025.11312644","title":"Incremental Policy Iteration for Unknown Nonlinear Systems with Stability and Performance Guarantees","display_name":"Incremental Policy Iteration for Unknown Nonlinear Systems with Stability and Performance Guarantees","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123359108","doi":"https://doi.org/10.1109/cdc57313.2025.11312644"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5004841687","display_name":"Qingkai Meng","orcid":"https://orcid.org/0000-0003-3648-7490"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qingkai Meng","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore,117583"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore,117583","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122901442","display_name":"Fenglan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Fenglan Wang","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore,117583"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore,117583","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064240573","display_name":"Lin Zhao","orcid":"https://orcid.org/0000-0002-1078-887X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lin Zhao","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore,117583"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore,117583","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62951602,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"837","last_page":"843"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.984000027179718,"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":0.984000027179718,"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":0.004999999888241291,"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":0.0012000000569969416,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6467000246047974},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5315999984741211},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.4537000060081482},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4526999890804291},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4253999888896942},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.3783000111579895},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.3671000003814697},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.34310001134872437},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.33640000224113464}],"concepts":[{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6467000246047974},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6220999956130981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.536300003528595},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4537000060081482},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4526999890804291},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4253999888896942},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.373199999332428},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.34310001134872437},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.3269999921321869},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C9936470","wikidata":"https://www.wikidata.org/wiki/Q6510405","display_name":"Least-squares function approximation","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C115527620","wikidata":"https://www.wikidata.org/wiki/Q769909","display_name":"Nonlinear programming","level":3,"score":0.28110000491142273},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27399998903274536},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.26759999990463257},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C49847556","wikidata":"https://www.wikidata.org/wiki/Q3964631","display_name":"Explained sum of squares","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C145249878","wikidata":"https://www.wikidata.org/wiki/Q2835868","display_name":"Recursive least squares filter","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1976956127","https://openalex.org/W2024303516","https://openalex.org/W2048687352","https://openalex.org/W2142599741","https://openalex.org/W2189990206","https://openalex.org/W2333120204","https://openalex.org/W2467518411","https://openalex.org/W2496953169","https://openalex.org/W2554786300","https://openalex.org/W4224943597","https://openalex.org/W4388579564","https://openalex.org/W4393335339","https://openalex.org/W4398187819","https://openalex.org/W4406705583"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,47,52],"general":[4],"incremental":[5],"policy":[6,62,67],"iteration":[7],"adaptive":[8,40],"dynamic":[9],"programming":[10],"(ADP)":[11],"algorithm":[12],"for":[13,50],"model-free":[14],"robust":[15,77],"optimal":[16,61],"control":[17],"of":[18,79,86,98],"unknown":[19],"nonlinear":[20],"systems.":[21],"The":[22],"approach":[23],"integrates":[24],"recursive":[25],"least":[26],"squares":[27],"estimation":[28],"with":[29,64],"linear":[30],"ADP":[31],"principles,":[32],"which":[33],"greatly":[34],"simplifies":[35],"the":[36,60,76,80,84,96,99],"implementation":[37],"while":[38],"preserving":[39],"learning":[41,59],"capabilities.":[42],"In":[43],"particular,":[44],"we":[45,74,90],"develop":[46],"sufficient":[48],"condition":[49],"selecting":[51],"discount":[53],"factor":[54],"such":[55],"that":[56,68],"it":[57],"allows":[58],"starting":[63],"an":[65],"initial":[66],"is":[69],"not":[70],"necessarily":[71],"stabilizing.":[72],"Moreover,":[73],"characterize":[75],"stability":[78],"closed-loop":[81],"system":[82],"and":[83],"near-optimality":[85],"iterative":[87],"policies.":[88],"Finally,":[89],"perform":[91],"numerical":[92],"simulations":[93],"to":[94],"demonstrate":[95],"effectiveness":[97],"proposed":[100],"method.":[101]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-14T00:00:00"}