{"id":"https://openalex.org/W4391594896","doi":"https://doi.org/10.1080/01691864.2024.2309621","title":"Density estimation based soft actor-critic: deep reinforcement learning for static output feedback control with measurement noise","display_name":"Density estimation based soft actor-critic: deep reinforcement learning for static output feedback control with measurement noise","publication_year":2024,"publication_date":"2024-02-07","ids":{"openalex":"https://openalex.org/W4391594896","doi":"https://doi.org/10.1080/01691864.2024.2309621"},"language":"en","primary_location":{"id":"doi:10.1080/01691864.2024.2309621","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1080/01691864.2024.2309621","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":true,"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":"middle","author":{"id":"https://openalex.org/A5052680900","display_name":"Ye Tian","orcid":"https://orcid.org/0000-0003-4965-2459"},"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":"Ye Tian","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4965-2459","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":false,"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":3,"corresponding_author_ids":["https://openalex.org/A5100447503"],"corresponding_institution_ids":["https://openalex.org/I22299242","https://openalex.org/I39012071"],"apc_list":null,"apc_paid":null,"fwci":0.6623,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7171711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"38","issue":"6","first_page":"398","last_page":"409"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9959999918937683,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9959999918937683,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9883999824523926,"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9495999813079834,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.8039510250091553},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6681635975837708},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.6175026893615723},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6042450070381165},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6039272546768188},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.601934552192688},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5778306126594543},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5373934507369995},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5361207723617554},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.49604448676109314},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4704688489437103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30315130949020386},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.27959680557250977},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20443883538246155}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8039510250091553},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6681635975837708},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6175026893615723},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6042450070381165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6039272546768188},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.601934552192688},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5778306126594543},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5373934507369995},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5361207723617554},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.49604448676109314},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4704688489437103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30315130949020386},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.27959680557250977},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20443883538246155},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/01691864.2024.2309621","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1080/01691864.2024.2309621","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":[{"score":0.75,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"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/W41554520","https://openalex.org/W958993015","https://openalex.org/W2263122262","https://openalex.org/W2607868186","https://openalex.org/W2619016545","https://openalex.org/W2795496197","https://openalex.org/W2962946825","https://openalex.org/W2963647337","https://openalex.org/W2990747716","https://openalex.org/W3011736333","https://openalex.org/W3098237412","https://openalex.org/W3206480318","https://openalex.org/W3216772467","https://openalex.org/W4224220194","https://openalex.org/W4250179088","https://openalex.org/W4293849739","https://openalex.org/W4296121324","https://openalex.org/W4307817089","https://openalex.org/W4362500581","https://openalex.org/W6677916085","https://openalex.org/W6950609307"],"related_works":["https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1515117609","https://openalex.org/W1589140671","https://openalex.org/W4323315247","https://openalex.org/W131709709","https://openalex.org/W2294884454","https://openalex.org/W3169161914"],"abstract_inverted_index":{"The":[0,193],"state-of-the-art":[1],"deep":[2],"reinforcement":[3],"learning":[4,147],"(DRL)":[5],"methods,":[6],"including":[7],"Deep":[8],"Deterministic":[9],"Policy":[10,18],"Gradient":[11],"(DDPG),":[12],"Twin":[13],"Delayed":[14],"DDPG":[15],"(TD3),":[16],"Proximal":[17],"Optimization":[19],"(PPO),":[20],"Soft":[21],"Actor-Critic":[22],"(SAC),":[23],"among":[24],"others,":[25],"demonstrate":[26],"significant":[27],"capability":[28],"in":[29,154],"solving":[30],"the":[31,53,78,96,100,103,108,121,142,148,155,159,163,171,178,188],"optimal":[32,54,143,149,172],"static":[33,55],"state":[34],"feedback":[35,57],"control":[36,58],"(SSFC)":[37],"problem.":[38,174],"This":[39,85],"problem":[40,60],"can":[41],"be":[42],"modeled":[43],"as":[44],"a":[45,65,88,114,132],"fully":[46],"observed":[47],"Markov":[48],"decision":[49],"process":[50],"(MDP).":[51],"However,":[52],"output":[56],"(SOFC)":[59],"with":[61,82,181],"measurement":[62],"noise":[63],"is":[64,72,111,125,138,195],"typical":[66],"partially":[67],"observable":[68],"MDP":[69],"(POMDP),":[70],"which":[71,120],"difficult":[73],"to":[74,91,113,140,169,186],"solve,":[75],"especially":[76],"for":[77],"continuous":[79],"state-action-observation":[80],"space":[81],"high":[83],"dimensions.":[84],"paper":[86],"proposes":[87],"two-stage":[89],"framework":[90],"address":[92],"this":[93,130],"challenge.":[94],"In":[95],"laboratory":[97],"stage,":[98,157],"both":[99],"states":[101],"and":[102,162,177],"noisy":[104,160],"outputs":[105,161],"are":[106,167,184],"observable;":[107],"SOFC":[109,144,165,173],"policy":[110,145,166],"converted":[112],"constrained":[115,150],"stochastic":[116,151],"SSFC":[117],"policy,":[118],"of":[119,190],"probability":[122],"density":[123,133],"function":[124],"generally":[126],"not":[127],"analytical.":[128],"To":[129],"end,":[131],"estimation":[134],"based":[135],"SAC":[136],"algorithm":[137],"proposed":[139],"explore":[141],"by":[146],"SSFC.":[152],"Consequently,":[153],"real-world":[156],"only":[158],"learned":[164],"required":[168],"solve":[170],"Numerical":[175],"simulations":[176],"corresponding":[179],"experiments":[180],"robotic":[182],"arms":[183],"provided":[185],"illustrate":[187],"effectiveness":[189],"our":[191],"method.":[192],"code":[194],"available":[196],"at":[197],"https://github.com/RanKyoto/DE-SAC.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}