{"id":"https://openalex.org/W4407896337","doi":"https://doi.org/10.1080/01691864.2025.2468215","title":"Deep reinforcement learning for static noisy state feedback control with reward estimation","display_name":"Deep reinforcement learning for static noisy state feedback control with reward estimation","publication_year":2025,"publication_date":"2025-02-24","ids":{"openalex":"https://openalex.org/W4407896337","doi":"https://doi.org/10.1080/01691864.2025.2468215"},"language":"en","primary_location":{"id":"doi:10.1080/01691864.2025.2468215","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01691864.2025.2468215","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"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ran Wang","raw_affiliation_strings":["Kyoto University"],"raw_orcid":"https://orcid.org/0000-0002-2521-8589","affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenji Kashima","raw_affiliation_strings":["Kyoto University"],"raw_orcid":"https://orcid.org/0000-0002-2963-2584","affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100447503"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04226896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"5","first_page":"259","last_page":"272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9983000159263611,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9957000017166138,"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":0.8267660140991211},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6139277815818787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5820760726928711},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5642246007919312},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5209780335426331},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.518997311592102},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4811474084854126},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.46697354316711426},{"id":"https://openalex.org/keywords/feedback-control","display_name":"Feedback control","score":0.4379338324069977},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4212411642074585},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3202611207962036},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2814064025878906},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11716166138648987}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8267660140991211},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6139277815818787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5820760726928711},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5642246007919312},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5209780335426331},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.518997311592102},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4811474084854126},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.46697354316711426},{"id":"https://openalex.org/C3018651601","wikidata":"https://www.wikidata.org/wiki/Q183635","display_name":"Feedback control","level":2,"score":0.4379338324069977},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4212411642074585},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3202611207962036},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2814064025878906},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11716166138648987},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/01691864.2025.2468215","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01691864.2025.2468215","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.44999998807907104}],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1539216098","https://openalex.org/W1583837637","https://openalex.org/W2055418958","https://openalex.org/W2074878962","https://openalex.org/W2145339207","https://openalex.org/W2260756217","https://openalex.org/W2607868186","https://openalex.org/W2781726626","https://openalex.org/W2795496197","https://openalex.org/W2914584698","https://openalex.org/W2962946825","https://openalex.org/W2963647337","https://openalex.org/W2970528191","https://openalex.org/W3216772467","https://openalex.org/W4214717370","https://openalex.org/W4297964528","https://openalex.org/W4367016688","https://openalex.org/W4391594896","https://openalex.org/W6677916085"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}