{"id":"https://openalex.org/W4386699389","doi":"https://doi.org/10.1109/access.2023.3314750","title":"Deep Adversarial Reinforcement Learning Method to Generate Control Policies Robust Against Worst-Case Value Predictions","display_name":"Deep Adversarial Reinforcement Learning Method to Generate Control Policies Robust Against Worst-Case Value Predictions","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386699389","doi":"https://doi.org/10.1109/access.2023.3314750"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3314750","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3314750","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10250423.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10250423.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020154047","display_name":"Kohei Ohashi","orcid":"https://orcid.org/0000-0002-9116-0952"},"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":"Kohei Ohashi","raw_affiliation_strings":["Department of Systems Science, Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Science, Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023583630","display_name":"Kosuke Nakanishi","orcid":"https://orcid.org/0000-0002-0078-6942"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]},{"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":"Kosuke Nakanishi","raw_affiliation_strings":["Department of Systems Science, Graduate School of Informatics, Kyoto University, Kyoto, Japan","Honda R&D Innovative Research Center, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0078-6942","affiliations":[{"raw_affiliation_string":"Department of Systems Science, Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Honda R&D Innovative Research Center, Tokyo, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109523475","display_name":"Yuji Yasui","orcid":null},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuji Yasui","raw_affiliation_strings":["Honda Research and Development Company Ltd., Saitama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research and Development Company Ltd., Saitama, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072540019","display_name":"Shin Ishii","orcid":"https://orcid.org/0000-0001-9385-8230"},"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/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shin Ishii","raw_affiliation_strings":["Department of Systems Science, Graduate School of Informatics, Kyoto University, Kyoto, Japan","International Research Center for Neurointelligence (WPI-IRCN), University of Tokyo Institutes for Advanced Study The University of Tokyo, Tokyo, Japan","Advanced Telecommunications Research Institute International (ATR), Seika, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Science, Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"International Research Center for Neurointelligence (WPI-IRCN), University of Tokyo Institutes for Advanced Study The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Advanced Telecommunications Research Institute International (ATR), Seika, Japan","institution_ids":["https://openalex.org/I4210104143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.8158,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78377307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"11","issue":null,"first_page":"100798","last_page":"100809"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998000264167786,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998000264167786,"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/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"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9818000197410583,"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/adversarial-system","display_name":"Adversarial system","score":0.9176968336105347},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8826131820678711},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7314810156822205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6976945996284485},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6693236827850342},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5973303318023682},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.533456563949585},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5150017738342285},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.44690531492233276},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.25549060106277466},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13894152641296387}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9176968336105347},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8826131820678711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7314810156822205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6976945996284485},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6693236827850342},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5973303318023682},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.533456563949585},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5150017738342285},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.44690531492233276},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.25549060106277466},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13894152641296387},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3314750","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3314750","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10250423.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f646c54671da448f9ed62a431b72a8f7","is_oa":true,"landing_page_url":"https://doaj.org/article/f646c54671da448f9ed62a431b72a8f7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 100798-100809 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3314750","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3314750","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10250423.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3173999216","display_name":null,"funder_award_id":"22H04998","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4096002373","display_name":null,"funder_award_id":"23H04676","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6177352223","display_name":null,"funder_award_id":"19H04180","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320321034","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386699389.pdf","grobid_xml":"https://content.openalex.org/works/W4386699389.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1673923490","https://openalex.org/W1686810756","https://openalex.org/W1945616565","https://openalex.org/W2017957151","https://openalex.org/W2105078254","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2155007355","https://openalex.org/W2156530608","https://openalex.org/W2163605009","https://openalex.org/W2180612164","https://openalex.org/W2194775991","https://openalex.org/W2243397390","https://openalex.org/W2602963933","https://openalex.org/W2766447205","https://openalex.org/W2773525213","https://openalex.org/W2773691349","https://openalex.org/W2911506106","https://openalex.org/W2949103145","https://openalex.org/W2962736495","https://openalex.org/W2963564844","https://openalex.org/W2963864421","https://openalex.org/W2982312374","https://openalex.org/W2996343955","https://openalex.org/W3098237412","https://openalex.org/W3124446631","https://openalex.org/W3131738409","https://openalex.org/W3172611073","https://openalex.org/W3209446190","https://openalex.org/W4300511536","https://openalex.org/W4302570325","https://openalex.org/W4306177393","https://openalex.org/W6631190155","https://openalex.org/W6637162671","https://openalex.org/W6637373629","https://openalex.org/W6640425456","https://openalex.org/W6682849425","https://openalex.org/W6684191040","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6719080892","https://openalex.org/W6733049761","https://openalex.org/W6735677848","https://openalex.org/W6747027214","https://openalex.org/W6762427411","https://openalex.org/W6774966973","https://openalex.org/W6789484704","https://openalex.org/W6797106545","https://openalex.org/W6845898014"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W4246396837","https://openalex.org/W2482350142","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W2294590153","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"Over":[0],"the":[1,89,94,168],"last":[2],"decade,":[3],"methods":[4,118],"for":[5,77,133,147],"autonomous":[6,37],"control":[7,38,71],"by":[8],"artificial":[9],"intelligence":[10],"have":[11],"been":[12],"extensively":[13],"developed":[14],"based":[15],"on":[16],"deep":[17,131,143],"reinforcement":[18],"learning":[19,55,63,106,155],"(DRL)":[20],"technologies.":[21],"However,":[22],"despite":[23],"these":[24,61,82],"advances,":[25],"robustness":[26,160],"to":[27,58,68,87,92,111,121,167,171],"noise":[28,165],"in":[29,36,43,136,150],"observation":[30],"data":[31],"remains":[32],"as":[33,126],"an":[34],"issue":[35],"policies":[39,65],"implemented":[40,125],"using":[41],"DRL":[42,109],"practical":[44],"applications.":[45],"In":[46],"this":[47],"study,":[48],"we":[49],"present":[50],"a":[51,101,113,127,130,142],"general":[52],"robust":[53],"adversarial":[54,62,78,83,154,162],"technology":[56],"applicable":[57],"DRL.":[59],"During":[60],"processes,":[64],"are":[66,85],"trained":[67],"output":[69],"consistent":[70],"actions":[72],"through":[73],"regularization":[74,105],"learning,":[75],"even":[76],"input":[79,169],"examples.":[80],"Importantly,":[81],"examples":[84],"produced":[86],"lead":[88],"current":[90],"policy":[91,145],"predict":[93],"worst":[95],"action":[96],"at":[97],"each":[98],"state.":[99],"Although":[100],"naive":[102],"implementation":[103],"of":[104,129,141],"may":[107],"cause":[108],"model":[110],"learn":[112],"biased":[114],"objective":[115],"function,":[116],"our":[117,152],"were":[119],"found":[120],"minimize":[122],"bias.":[123],"When":[124],"modification":[128],"Q-network":[132],"discrete-action":[134],"problems":[135],"Atari":[137],"2600":[138],"games":[139],"and":[140,163],"deterministic":[144],"gradient":[146],"continuous-action":[148],"tasks":[149],"Pybullet,":[151],"new":[153],"frameworks":[156],"showed":[157],"significantly":[158],"enhanced":[159],"against":[161],"random":[164],"added":[166],"compared":[170],"several":[172],"recently":[173],"proposed":[174],"methods.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}