{"id":"https://openalex.org/W4382931276","doi":"https://doi.org/10.1080/01691864.2023.2229886","title":"Deep reinforcement learning for continuous-time self-triggered control with experimental evaluation","display_name":"Deep reinforcement learning for continuous-time self-triggered control with experimental evaluation","publication_year":2023,"publication_date":"2023-07-03","ids":{"openalex":"https://openalex.org/W4382931276","doi":"https://doi.org/10.1080/01691864.2023.2229886"},"language":"en","primary_location":{"id":"doi:10.1080/01691864.2023.2229886","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01691864.2023.2229886","pdf_url":null,"source":{"id":"https://openalex.org/S192584203","display_name":"Advanced Robotics","issn_l":"0169-1864","issn":["0169-1864","1568-5535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Robotics","raw_type":"journal-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/A5100447503","display_name":"Ran Wang","orcid":"https://orcid.org/0000-0002-2521-8589"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ran Wang","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2521-8589","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066521241","display_name":"Kenji Kashima","orcid":"https://orcid.org/0000-0002-2963-2584"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kenji Kashima","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2963-2584","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5066521241"],"corresponding_institution_ids":["https://openalex.org/I22299242","https://openalex.org/I39012071"],"apc_list":null,"apc_paid":null,"fwci":0.5819,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70532395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"37","issue":"16","first_page":"1012","last_page":"1024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9984999895095825,"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":0.9984999895095825,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.9941999912261963,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9940000176429749,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8725116848945618},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.6940165758132935},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6540937423706055},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6026502251625061},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.577728271484375},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.548796534538269},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5463682413101196},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3019251823425293},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.060834020376205444}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8725116848945618},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.6940165758132935},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6540937423706055},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6026502251625061},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.577728271484375},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.548796534538269},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5463682413101196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3019251823425293},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.060834020376205444},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/01691864.2023.2229886","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01691864.2023.2229886","pdf_url":null,"source":{"id":"https://openalex.org/S192584203","display_name":"Advanced Robotics","issn_l":"0169-1864","issn":["0169-1864","1568-5535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Robotics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7136757290","display_name":null,"funder_award_id":"JP21H04875","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1511275238","https://openalex.org/W1973378833","https://openalex.org/W1985235885","https://openalex.org/W2017957151","https://openalex.org/W2046376809","https://openalex.org/W2134458410","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2593237273","https://openalex.org/W2605628695","https://openalex.org/W2772589676","https://openalex.org/W2781726626","https://openalex.org/W2889856497","https://openalex.org/W2973005513","https://openalex.org/W3014507210","https://openalex.org/W3100789280","https://openalex.org/W3210928827","https://openalex.org/W4205353506","https://openalex.org/W4214717370","https://openalex.org/W6684205842"],"related_works":["https://openalex.org/W2904902274","https://openalex.org/W3196329154","https://openalex.org/W2088253028","https://openalex.org/W90056650","https://openalex.org/W1573267871","https://openalex.org/W3016250019","https://openalex.org/W2005150327","https://openalex.org/W1442549794","https://openalex.org/W2753642519","https://openalex.org/W2985170256"],"abstract_inverted_index":{"This":[0],"paper":[1],"develops":[2],"a":[3,21,87],"deterministic":[4],"policy":[5,44],"gradient":[6],"(DPG)":[7],"method":[8],"for":[9,26,80],"self-triggered":[10],"control":[11,30,40,53],"(STC)":[12],"on":[13],"continuous-time":[14],"systems.":[15],"To":[16],"this":[17],"end,":[18],"we":[19],"propose":[20],"reinforcement":[22],"learning":[23],"(RL)":[24],"algorithm":[25],"STC.":[27],"In":[28],"general,":[29],"systems":[31],"have":[32],"high":[33,74],"sampling":[34,48],"rate":[35,49],"(communication":[36],"cost)":[37],"to":[38,97],"guarantee":[39],"performance.":[41,54],"However,":[42],"STC":[43],"allows":[45],"reducing":[46],"the":[47,58,61,67,78,92,99,102],"while":[50],"maintaining":[51],"reasonable":[52],"Moreover,":[55],"it":[56],"compresses":[57],"size":[59],"of":[60,86,101],"historical":[62],"data":[63,68,75],"set,":[64],"slowing":[65],"down":[66],"explosion.":[69],"The":[70],"STC-based":[71],"RL":[72],"demonstrates":[73],"efficiency":[76],"and":[77,91],"potential":[79],"industrial":[81],"applications.":[82],"A":[83],"numerical":[84],"simulation":[85],"rotary":[88],"inverted":[89],"pendulum":[90],"corresponding":[93],"experiments":[94],"are":[95],"employed":[96],"show":[98],"effectiveness":[100],"algorithm.":[103]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}