{"id":"https://openalex.org/W3108840433","doi":"https://doi.org/10.1109/codit49905.2020.9263879","title":"On-policy Approximate Dynamic Programming for Optimal Control of non-linear systems","display_name":"On-policy Approximate Dynamic Programming for Optimal Control of non-linear systems","publication_year":2020,"publication_date":"2020-06-29","ids":{"openalex":"https://openalex.org/W3108840433","doi":"https://doi.org/10.1109/codit49905.2020.9263879","mag":"3108840433"},"language":"en","primary_location":{"id":"doi:10.1109/codit49905.2020.9263879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit49905.2020.9263879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 7th International Conference on Control, Decision and Information Technologies (CoDIT)","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/A5033955545","display_name":"K. Shalini","orcid":"https://orcid.org/0000-0003-4099-7979"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shalini K","raw_affiliation_strings":["EED, Veermata Jijabai Technological Institute, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"EED, Veermata Jijabai Technological Institute, Mumbai, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108730388","display_name":"D. Vrushabh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D. Vrushabh","raw_affiliation_strings":["EED, Veermata Jijabai Technological Institute, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"EED, Veermata Jijabai Technological Institute, Mumbai, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033955545","display_name":"K. Shalini","orcid":"https://orcid.org/0000-0003-4099-7979"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K. Shalini","raw_affiliation_strings":["EED, Veermata Jijabai Technological Institute, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"EED, Veermata Jijabai Technological Institute, Mumbai, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033955545"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18978855,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":null,"first_page":"1058","last_page":"1062"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"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":1.0,"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":0.9804999828338623,"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":0.9366000294685364,"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/hamilton\u2013jacobi\u2013bellman-equation","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","score":0.9743037819862366},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.7736590504646301},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.7093691825866699},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6916247010231018},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5690370798110962},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.555512011051178},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.418326735496521},{"id":"https://openalex.org/keywords/partial-differential-equation","display_name":"Partial differential equation","score":0.41224777698516846},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.34013962745666504},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.08900013566017151}],"concepts":[{"id":"https://openalex.org/C196978813","wikidata":"https://www.wikidata.org/wiki/Q3302775","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","level":3,"score":0.9743037819862366},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.7736590504646301},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.7093691825866699},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6916247010231018},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5690370798110962},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.555512011051178},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.418326735496521},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.41224777698516846},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.34013962745666504},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08900013566017151},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/codit49905.2020.9263879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit49905.2020.9263879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 7th International Conference on Control, Decision and Information Technologies (CoDIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2037157222","https://openalex.org/W2048687352","https://openalex.org/W2093831009","https://openalex.org/W2108286682","https://openalex.org/W2120346334","https://openalex.org/W2154077222","https://openalex.org/W2165726932","https://openalex.org/W2189990206","https://openalex.org/W2341171179","https://openalex.org/W2523246573","https://openalex.org/W2586680856","https://openalex.org/W2919774326","https://openalex.org/W2969945254","https://openalex.org/W3193283090","https://openalex.org/W4237591687","https://openalex.org/W4285719527","https://openalex.org/W6677737365","https://openalex.org/W6727249380","https://openalex.org/W6799835771"],"related_works":["https://openalex.org/W4239477580","https://openalex.org/W4255265352","https://openalex.org/W2921905705","https://openalex.org/W1632524629","https://openalex.org/W4292330635","https://openalex.org/W2902017027","https://openalex.org/W2766998270","https://openalex.org/W2950982235","https://openalex.org/W4306892756","https://openalex.org/W2052286527"],"abstract_inverted_index":{"Optimal":[0],"control":[1,21,105,146],"theory":[2],"deals":[3],"with":[4],"finding":[5,18],"the":[6,10,19,23,26,34,39,43,62,69,73,88,93,99,121,137,140,156],"policy":[7,94,106],"that":[8,50],"minimizes":[9],"discounted":[11],"infinite":[12],"horizon":[13],"quadratic":[14],"cost":[15],"function.":[16,127],"For":[17],"optimal":[20],"policy,":[22],"solution":[24,86],"of":[25,87,101,123,139,158],"Hamilton-Jacobi-Bellman":[27],"(HJB)":[28],"equation":[29,49,71],"must":[30],"be":[31],"found":[32,91],"i.e.":[33],"value":[35,108],"function":[36,109,113],"which":[37,97],"satisfies":[38],"Bellman":[40],"equation.":[41],"However,":[42],"HJB":[44,70,89],"is":[45,51,90,133,148,161],"a":[46,56],"partial":[47],"differential":[48],"difficult":[52],"to":[53,67,135],"solve":[54,68],"for":[55,72,150],"nonlinear":[57,75],"system.":[58],"The":[59,84,104,128,145],"paper":[60],"employs":[61],"approximate":[63,85],"dynamic":[64],"programming":[65],"method":[66],"deterministic":[74],"discrete-time":[76],"systems":[77],"in":[78,120,163],"continuous":[79],"state":[80],"and":[81,107,142],"action":[82],"space.":[83],"by":[92],"iteration":[95],"algorithm":[96,132,147],"has":[98],"framework":[100],"actor-critic":[102],"architecture.":[103],"are":[110],"approximated":[111],"using":[112],"approximators":[114],"such":[115],"as":[116],"neural":[117],"network":[118],"represented":[119],"form":[122],"linearly":[124],"independent":[125],"basis":[126],"gradient":[129],"descent":[130],"optimization":[131],"employed":[134],"tune":[136],"weights":[138],"actor":[141],"critic":[143],"network.":[144],"implemented":[149],"cart":[151],"pole":[152],"inverted":[153],"pendulum":[154],"system,":[155],"effectiveness":[157],"this":[159],"approach":[160],"provided":[162],"simulations.":[164]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}