{"id":"https://openalex.org/W7138028301","doi":"https://doi.org/10.1609/aaai.v40i27.39421","title":"Physics-Informed Approach for Exploratory Hamilton\u2013Jacobi\u2013Bellman Equations via Policy Iterations","display_name":"Physics-Informed Approach for Exploratory Hamilton\u2013Jacobi\u2013Bellman Equations via Policy Iterations","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138028301","doi":"https://doi.org/10.1609/aaai.v40i27.39421"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i27.39421","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i27.39421","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i27.39421","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091851063","display_name":"Yeongjong Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]},{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yeongjong Kim","raw_affiliation_strings":["Pohang University of Science and Technology","Seoul National University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pohang University of Science and Technology","institution_ids":["https://openalex.org/I123900574"]},{"raw_affiliation_string":"Seoul National University of Science and Technology","institution_ids":["https://openalex.org/I118373667"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129748218","display_name":"Namkyeong Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I12832649","display_name":"Gachon University","ror":"https://ror.org/03ryywt80","country_code":"KR","type":"education","lineage":["https://openalex.org/I12832649"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Namkyeong Cho","raw_affiliation_strings":["Gachon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gachon University","institution_ids":["https://openalex.org/I12832649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129743559","display_name":"Minseok Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minseok Kim","raw_affiliation_strings":["Seoul National University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University of Science and Technology","institution_ids":["https://openalex.org/I118373667"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028468023","display_name":"Yeoneung Kim","orcid":"https://orcid.org/0000-0001-6293-3939"},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]},{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeoneung Kim","raw_affiliation_strings":["Pohang University of Science and Technology","Seoul National University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pohang University of Science and Technology","institution_ids":["https://openalex.org/I123900574"]},{"raw_affiliation_string":"Seoul National University of Science and Technology","institution_ids":["https://openalex.org/I118373667"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091851063"],"corresponding_institution_ids":["https://openalex.org/I118373667","https://openalex.org/I123900574"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24489796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"27","first_page":"22609","last_page":"22616"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.8758999705314636,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.8758999705314636,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.07199999690055847,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.011099999770522118,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6478999853134155},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5863999724388123},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.572700023651123},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5317000150680542},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4731000065803528},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.45089998841285706},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.3598000109195709},{"id":"https://openalex.org/keywords/approximation-error","display_name":"Approximation error","score":0.3174999952316284}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6478999853134155},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5863999724388123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5827999711036682},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.572700023651123},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5317000150680542},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4731000065803528},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4717999994754791},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.45089998841285706},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36230000853538513},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3434000015258789},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.30709999799728394},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C48753275","wikidata":"https://www.wikidata.org/wiki/Q11216","display_name":"Numerical analysis","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2547000050544739},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i27.39421","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i27.39421","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i27.39421","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i27.39421","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,40],"propose":[1],"a":[2,42,70],"mesh-free":[3],"policy":[4,25,57],"iteration":[5,55],"framework":[6],"based":[7],"on":[8,37],"physics-informed":[9],"neural":[10,33],"networks":[11],"(PINNs)":[12],"for":[13],"solving":[14],"entropy-regularized":[15],"stochastic":[16],"control":[17,74],"problems.":[18,94],"The":[19,64],"method":[20],"iteratively":[21],"alternates":[22],"between":[23],"soft":[24],"evaluation":[26],"and":[27,32,60,82,92,101,109],"improvement":[28],"using":[29],"automatic":[30],"differentiation":[31],"approximation,":[34],"without":[35],"relying":[36],"spatial":[38],"discretization.":[39],"present":[41],"detailed":[43],"error":[44,51],"analysis":[45],"that":[46],"decomposes":[47],"the":[48,98],"total":[49],"approximation":[50],"into":[52],"three":[53],"sources:":[54],"error,":[56,59],"network":[58],"PDE":[61],"residual":[62],"error.":[63],"proposed":[65],"algorithm":[66],"is":[67],"validated":[68],"with":[69],"range":[71],"of":[72,103],"challenging":[73],"tasks,":[75],"including":[76],"high-dimensional":[77],"linear-quadratic":[78],"regulation":[79],"in":[80],"5D":[81],"10D,":[83],"as":[84,86,90],"well":[85],"nonlinear":[87,110],"systems":[88],"such":[89],"pendulum":[91],"cartpole":[93],"Numerical":[95],"results":[96],"confirm":[97],"scalability,":[99],"accuracy,":[100],"robustness":[102],"our":[104],"approach":[105],"across":[106],"both":[107],"linear":[108],"benchmarks.":[111]},"counts_by_year":[],"updated_date":"2026-05-21T09:19:25.381259","created_date":"2026-03-18T00:00:00"}