{"id":"https://openalex.org/W3010680978","doi":"https://doi.org/10.1109/cdc40024.2019.9028930","title":"On Improving the Robustness of Reinforcement Learning-based Controllers using Disturbance Observer","display_name":"On Improving the Robustness of Reinforcement Learning-based Controllers using Disturbance Observer","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3010680978","doi":"https://doi.org/10.1109/cdc40024.2019.9028930","mag":"3010680978"},"language":"en","primary_location":{"id":"doi:10.1109/cdc40024.2019.9028930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9028930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","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/A5082592137","display_name":"Jeong Woo Kim","orcid":"https://orcid.org/0000-0003-1580-1006"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jeong Woo Kim","raw_affiliation_strings":["ASRI, Seoul National University, Korea"],"affiliations":[{"raw_affiliation_string":"ASRI, Seoul National University, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055470439","display_name":"Hyungbo Shim","orcid":"https://orcid.org/0000-0002-5972-8114"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungbo Shim","raw_affiliation_strings":["ASRI, Seoul National University, Korea"],"affiliations":[{"raw_affiliation_string":"ASRI, Seoul National University, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063507594","display_name":"Insoon Yang","orcid":"https://orcid.org/0000-0001-5887-6169"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Insoon Yang","raw_affiliation_strings":["ASRI, Seoul National University, Korea"],"affiliations":[{"raw_affiliation_string":"ASRI, Seoul National University, Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082592137"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":1.9992,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.88339797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"847","last_page":"852"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9965999722480774,"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":0.9911999702453613,"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/robustness","display_name":"Robustness (evolution)","score":0.8430912494659424},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7665181159973145},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7484252452850342},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6766455173492432},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4925428330898285},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.49013957381248474},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.4889203608036041},{"id":"https://openalex.org/keywords/disturbance","display_name":"Disturbance (geology)","score":0.46450018882751465},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.3953261375427246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2812243700027466},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.25819939374923706},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21512377262115479},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11066949367523193}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8430912494659424},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7665181159973145},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7484252452850342},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6766455173492432},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4925428330898285},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.49013957381248474},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.4889203608036041},{"id":"https://openalex.org/C2777601987","wikidata":"https://www.wikidata.org/wiki/Q5283581","display_name":"Disturbance (geology)","level":2,"score":0.46450018882751465},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3953261375427246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2812243700027466},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25819939374923706},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21512377262115479},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11066949367523193},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc40024.2019.9028930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9028930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:s-space.snu.ac.kr:10371/198095","is_oa":false,"landing_page_url":"https://hdl.handle.net/10371/198095","pdf_url":null,"source":{"id":"https://openalex.org/S4306401345","display_name":"Seoul National University Open Repository (Seoul National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139264467","host_organization_name":"Seoul National University","host_organization_lineage":["https://openalex.org/I139264467"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W560518094","https://openalex.org/W1614417283","https://openalex.org/W1771410628","https://openalex.org/W2073990179","https://openalex.org/W2086767939","https://openalex.org/W2093865329","https://openalex.org/W2120038868","https://openalex.org/W2236026133","https://openalex.org/W2736601468","https://openalex.org/W2739330054","https://openalex.org/W2911087563","https://openalex.org/W2914316834","https://openalex.org/W2963525569","https://openalex.org/W2964114602","https://openalex.org/W3105722772","https://openalex.org/W4205326910","https://openalex.org/W4294555834","https://openalex.org/W4301886962","https://openalex.org/W6634528131","https://openalex.org/W6638018090","https://openalex.org/W6737214707","https://openalex.org/W6738483526","https://openalex.org/W6741002519"],"related_works":["https://openalex.org/W2038604956","https://openalex.org/W2296560746","https://openalex.org/W2338222801","https://openalex.org/W2347583731","https://openalex.org/W2106602008","https://openalex.org/W2067832159","https://openalex.org/W2153353177","https://openalex.org/W3156121563","https://openalex.org/W2355389557","https://openalex.org/W1980376593"],"abstract_inverted_index":{"Because":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"may":[4,31],"cause":[5],"issues":[6],"in":[7,35],"stability":[8],"and":[9,46,79,81],"safety":[10],"when":[11,118],"directly":[12],"applied":[13,99],"to":[14,22,40,56,84,100,120],"physical":[15,122],"systems,":[16],"a":[17,24,36,114],"simulator":[18,45],"is":[19],"often":[20],"used":[21],"learn":[23],"control":[25,29],"policy.":[26],"However,":[27],"the":[28,41,44,47,58,66,74,77,86,94,110,121],"performance":[30,88,116],"be":[32,98],"easily":[33],"deteriorated":[34],"real":[37],"plant":[38,78],"due":[39],"discrepancy":[42],"between":[43,76],"plant.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"propose":[53],"an":[54],"idea":[55],"enhance":[57],"robustness":[59],"of":[60],"such":[61],"RL-based":[62],"controllers":[63],"by":[64],"utilizing":[65],"disturbance":[67,83],"observer":[68],"(DOB).":[69],"This":[70],"method":[71],"compensates":[72],"for":[73],"mismatch":[75],"simulator,":[80],"rejects":[82],"maintain":[85],"nominal":[87],"while":[89],"guaranteeing":[90],"robust":[91],"stability.":[92],"Furthermore,":[93],"proposed":[95],"approach":[96],"can":[97],"partially":[101],"observable":[102],"systems.":[103],"We":[104],"also":[105],"characterize":[106],"conditions":[107],"under":[108],"which":[109],"learned":[111],"controller":[112],"has":[113],"provable":[115],"bound":[117],"connected":[119],"system.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}