{"id":"https://openalex.org/W3112280718","doi":"https://doi.org/10.1109/smc42975.2020.9283087","title":"Robust Control in the Worst Case Using Continuous Time Reinforcement Learning","display_name":"Robust Control in the Worst Case Using Continuous Time Reinforcement Learning","publication_year":2020,"publication_date":"2020-10-11","ids":{"openalex":"https://openalex.org/W3112280718","doi":"https://doi.org/10.1109/smc42975.2020.9283087","mag":"3112280718"},"language":"en","primary_location":{"id":"doi:10.1109/smc42975.2020.9283087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc42975.2020.9283087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5065156490","display_name":"Adolfo Perrusqu\u00eda","orcid":"https://orcid.org/0000-0003-2290-1160"},"institutions":[{"id":"https://openalex.org/I68368234","display_name":"Center for Research and Advanced Studies of the National Polytechnic Institute","ror":"https://ror.org/009eqmr18","country_code":"MX","type":"facility","lineage":["https://openalex.org/I59361560","https://openalex.org/I68368234"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Adolfo Perrusquia","raw_affiliation_strings":["CINVESTAV-IPN, Mexico City, Mexico"],"affiliations":[{"raw_affiliation_string":"CINVESTAV-IPN, Mexico City, Mexico","institution_ids":["https://openalex.org/I68368234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008201587","display_name":"Wen Yu","orcid":"https://orcid.org/0000-0002-9540-7924"},"institutions":[{"id":"https://openalex.org/I68368234","display_name":"Center for Research and Advanced Studies of the National Polytechnic Institute","ror":"https://ror.org/009eqmr18","country_code":"MX","type":"facility","lineage":["https://openalex.org/I59361560","https://openalex.org/I68368234"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Wen Yu","raw_affiliation_strings":["CINVESTAV-IPN, Mexico City, Mexico"],"affiliations":[{"raw_affiliation_string":"CINVESTAV-IPN, Mexico City, Mexico","institution_ids":["https://openalex.org/I68368234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100683740","display_name":"Xiaoou Li","orcid":"https://orcid.org/0000-0003-3087-7375"},"institutions":[{"id":"https://openalex.org/I68368234","display_name":"Center for Research and Advanced Studies of the National Polytechnic Institute","ror":"https://ror.org/009eqmr18","country_code":"MX","type":"facility","lineage":["https://openalex.org/I59361560","https://openalex.org/I68368234"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Xiaoou Li","raw_affiliation_strings":["CINVESTAV-IPN, Mexico City, Mexico"],"affiliations":[{"raw_affiliation_string":"CINVESTAV-IPN, Mexico City, Mexico","institution_ids":["https://openalex.org/I68368234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065156490"],"corresponding_institution_ids":["https://openalex.org/I68368234"],"apc_list":null,"apc_paid":null,"fwci":0.1407,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55059309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1951","last_page":"1954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994000196456909,"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":0.9718999862670898,"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":0.901376485824585},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7107061147689819},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.6130005717277527},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6058313846588135},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5188666582107544},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5030712485313416},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4829629957675934},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4411117136478424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.424937903881073},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41531819105148315},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4114112854003906},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4046825170516968},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.2691006362438202},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2399941086769104},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19201460480690002},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12894389033317566}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.901376485824585},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7107061147689819},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.6130005717277527},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6058313846588135},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5188666582107544},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5030712485313416},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4829629957675934},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4411117136478424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.424937903881073},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41531819105148315},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4114112854003906},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4046825170516968},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2691006362438202},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2399941086769104},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19201460480690002},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12894389033317566},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc42975.2020.9283087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc42975.2020.9283087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W202760110","https://openalex.org/W1553308207","https://openalex.org/W1568229137","https://openalex.org/W1626155273","https://openalex.org/W1729165410","https://openalex.org/W1966086707","https://openalex.org/W1977655452","https://openalex.org/W1983523797","https://openalex.org/W1991927580","https://openalex.org/W2011694027","https://openalex.org/W2020539709","https://openalex.org/W2026661001","https://openalex.org/W2065253294","https://openalex.org/W2074500080","https://openalex.org/W2099767582","https://openalex.org/W2103791569","https://openalex.org/W2113501460","https://openalex.org/W2115299867","https://openalex.org/W2121863487","https://openalex.org/W2559552201","https://openalex.org/W2633195366","https://openalex.org/W2754627144","https://openalex.org/W2895609205","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W6634111601","https://openalex.org/W6653405796","https://openalex.org/W6666690043","https://openalex.org/W6730127735"],"related_works":["https://openalex.org/W1585007175","https://openalex.org/W2382521049","https://openalex.org/W4306904969","https://openalex.org/W2144385241","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W1980376593"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,19],"(RL)":[2],"is":[3,48],"an":[4],"effective":[5],"method":[6,47],"to":[7],"design":[8],"robust":[9,53],"control.":[10],"Uncertainty":[11],"in":[12],"the":[13,35,42,55],"worst":[14],"case":[15],"requires":[16],"large":[17],"state-action":[18],"space.":[20],"The":[21],"continuous":[22,37],"time":[23,38],"RL":[24],"can":[25],"solve":[26],"this":[27,31],"computational":[28],"problem.":[29],"In":[30],"paper,":[32],"we":[33],"modify":[34],"classical":[36],"RL.":[39],"Compared":[40],"with":[41],"actor-critic":[43],"(AC)":[44],"algorithm,":[45],"our":[46],"more":[49,52],"simple":[50],"and":[51],"under":[54],"worst-case":[56],"uncertainty.":[57]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}