{"id":"https://openalex.org/W7124156811","doi":"https://doi.org/10.1109/codit66093.2025.11321592","title":"Piecewise Reinforcement Learning for Hybrid Systems","display_name":"Piecewise Reinforcement Learning for Hybrid Systems","publication_year":2025,"publication_date":"2025-07-15","ids":{"openalex":"https://openalex.org/W7124156811","doi":"https://doi.org/10.1109/codit66093.2025.11321592"},"language":null,"primary_location":{"id":"doi:10.1109/codit66093.2025.11321592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit66093.2025.11321592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 11th 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/A5123047378","display_name":"Mi Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136895","display_name":"Institute for the Future","ror":"https://ror.org/049tcsg76","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210136895"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mi Zhou","raw_affiliation_strings":["Futurewei Technologies,San Jose,CA,30332"],"affiliations":[{"raw_affiliation_string":"Futurewei Technologies,San Jose,CA,30332","institution_ids":["https://openalex.org/I4210136895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035870473","display_name":"Jiazhi Li","orcid":"https://orcid.org/0000-0001-9744-6110"},"institutions":[{"id":"https://openalex.org/I4210136895","display_name":"Institute for the Future","ror":"https://ror.org/049tcsg76","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210136895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiazhi Li","raw_affiliation_strings":["Futurewei Technologies,San Jose,CA,30332"],"affiliations":[{"raw_affiliation_string":"Futurewei Technologies,San Jose,CA,30332","institution_ids":["https://openalex.org/I4210136895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123033900","display_name":"Masood Mortazavi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136895","display_name":"Institute for the Future","ror":"https://ror.org/049tcsg76","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210136895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masood Mortazavi","raw_affiliation_strings":["Futurewei Technologies,San Jose,CA,30332"],"affiliations":[{"raw_affiliation_string":"Futurewei Technologies,San Jose,CA,30332","institution_ids":["https://openalex.org/I4210136895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123042018","display_name":"Ning Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136895","display_name":"Institute for the Future","ror":"https://ror.org/049tcsg76","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210136895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ning Yan","raw_affiliation_strings":["Futurewei Technologies,San Jose,CA,30332"],"affiliations":[{"raw_affiliation_string":"Futurewei Technologies,San Jose,CA,30332","institution_ids":["https://openalex.org/I4210136895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025532495","display_name":"Chaouki T. Abdallah","orcid":"https://orcid.org/0000-0001-8259-097X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaouki Abdallah","raw_affiliation_strings":["Georgia Institute of Technology,School of Electrical and Computer Engineering,San Jose,CA,30332"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Electrical and Computer Engineering,San Jose,CA,30332","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5123047378"],"corresponding_institution_ids":["https://openalex.org/I4210136895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.77028886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2069","last_page":"2074"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.8331999778747559,"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":0.8331999778747559,"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":0.14229999482631683,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.0015999999595806003,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7975000143051147},{"id":"https://openalex.org/keywords/piecewise","display_name":"Piecewise","score":0.7257000207901001},{"id":"https://openalex.org/keywords/hybrid-system","display_name":"Hybrid system","score":0.5429999828338623},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.44699999690055847},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3628999888896942},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.3549000024795532}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7975000143051147},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.7257000207901001},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.5429999828338623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5242999792098999},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.46889999508857727},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4465999901294708},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4146000146865845},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3628999888896942},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C17095337","wikidata":"https://www.wikidata.org/wiki/Q2375229","display_name":"Piecewise linear function","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29170000553131104},{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/codit66093.2025.11321592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit66093.2025.11321592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 11th International Conference on Control, Decision and Information Technologies (CoDIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5362950563430786,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1481223045","https://openalex.org/W1487586009","https://openalex.org/W1538133856","https://openalex.org/W2037538889","https://openalex.org/W2039566400","https://openalex.org/W2057794519","https://openalex.org/W2112891890","https://openalex.org/W2116169923","https://openalex.org/W2143847391","https://openalex.org/W2221321873","https://openalex.org/W2259535384","https://openalex.org/W2593412525","https://openalex.org/W2804938478","https://openalex.org/W2973229164","https://openalex.org/W3011097823","https://openalex.org/W3022789369","https://openalex.org/W3046783666","https://openalex.org/W3119164477","https://openalex.org/W3169486517","https://openalex.org/W4223992650","https://openalex.org/W4294692130","https://openalex.org/W4382936242","https://openalex.org/W4395070225","https://openalex.org/W4409796500"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,35],"article,":[2],"a":[3],"state-dependent":[4,19],"piecewise":[5,29],"reinforcement":[6],"learning":[7,27],"(PRL)":[8],"method":[9,70],"is":[10,23,63],"proposed":[11],"to":[12,26,50],"learn":[13],"an":[14,24],"optimal":[15],"control":[16,31],"policy":[17,58,68],"for":[18],"switched":[20,77],"systems.":[21,88],"This":[22],"analogy":[25],"multiple":[28],"continuous":[30],"inputs.":[32],"We":[33,79],"observe":[34],"method\u2019s":[36],"robust":[37],"and":[38,47],"impressive":[39],"performance,":[40],"explain":[41],"it":[42,49],"in":[43,71,86],"rigorous":[44],"mathematical":[45],"language,":[46],"apply":[48],"some":[51],"canonical":[52],"examples.":[53],"Based":[54],"on":[55],"the":[56,61,66],"deterministic":[57],"gradient":[59,69],"method,":[60],"PRL":[62,83],"compared":[64],"with":[65,76],"vanilla":[67],"three":[72],"customized":[73],"demonstrative":[74],"environments":[75],"dynamics.":[78],"theoretically":[80],"demystify":[81],"why":[82],"outperforms":[84],"RL":[85],"these":[87]},"counts_by_year":[],"updated_date":"2026-01-16T23:16:36.188383","created_date":"2026-01-15T00:00:00"}