{"id":"https://openalex.org/W4403390458","doi":"https://doi.org/10.1109/access.2024.3479089","title":"Orthogonal Adversarial Deep Reinforcement Learning for Discrete- and Continuous-Action Problems","display_name":"Orthogonal Adversarial Deep Reinforcement Learning for Discrete- and Continuous-Action Problems","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403390458","doi":"https://doi.org/10.1109/access.2024.3479089"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3479089","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3479089","pdf_url":null,"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://doi.org/10.1109/access.2024.3479089","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/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"],"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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080224445","display_name":"Nao Goto","orcid":null},"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":"Nao Goto","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/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 Innovative Research Center, Tokyo, Japan","Honda R&D Innovative Research Center, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research and Development Innovative Research Center, Tokyo, Japan","institution_ids":["https://openalex.org/I1283473643"]},{"raw_affiliation_string":"Honda R&D Innovative Research Center, Tokyo, 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"]}],"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"],"raw_orcid":"https://orcid.org/0000-0001-9385-8230","affiliations":[{"raw_affiliation_string":"Department of Systems Science, Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.6109,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74483084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"12","issue":null,"first_page":"151907","last_page":"151919"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9096999764442444,"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":0.9096999764442444,"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":0.8098320364952087},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7135699987411499},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6991375088691711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.517484188079834},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5143498182296753}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8098320364952087},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7135699987411499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6991375088691711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.517484188079834},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5143498182296753},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3479089","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3479089","pdf_url":null,"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:d9f5c94576194944888428a60a9406e6","is_oa":true,"landing_page_url":"https://doaj.org/article/d9f5c94576194944888428a60a9406e6","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 12, Pp 151907-151919 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3479089","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3479089","pdf_url":null,"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":[{"display_name":"Reduced inequalities","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10"}],"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/G5760087609","display_name":null,"funder_award_id":"22H04998","funder_id":"https://openalex.org/F4320321034","funder_display_name":"New Energy and Industrial Technology Development Organization"},{"id":"https://openalex.org/G7489112994","display_name":null,"funder_award_id":"22H04998","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"}],"funders":[{"id":"https://openalex.org/F4320320212","display_name":"Japan Society for the Promotion of Science London","ror":"https://ror.org/02m7axw05"},{"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":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2105078254","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2180612164","https://openalex.org/W2194775991","https://openalex.org/W2243397390","https://openalex.org/W2603766943","https://openalex.org/W2773691349","https://openalex.org/W2904246096","https://openalex.org/W2911506106","https://openalex.org/W2962736495","https://openalex.org/W2963564844","https://openalex.org/W2963857521","https://openalex.org/W2981207549","https://openalex.org/W2982312374","https://openalex.org/W3200885897","https://openalex.org/W3209446190","https://openalex.org/W4386699389","https://openalex.org/W6631190155","https://openalex.org/W6634413486","https://openalex.org/W6637162671","https://openalex.org/W6637373629","https://openalex.org/W6640425456","https://openalex.org/W6682849425","https://openalex.org/W6684191040","https://openalex.org/W6684921986","https://openalex.org/W6733049761","https://openalex.org/W6735677848","https://openalex.org/W6747027214","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6762427411","https://openalex.org/W6762718338","https://openalex.org/W6774966973","https://openalex.org/W6789484704","https://openalex.org/W6797106545","https://openalex.org/W6845898014"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,30,97,165,241],"deep":[3,200,203],"neural":[4],"network":[5],"(DNN)":[6],"technology":[7],"are":[8,67,92],"enhancing":[9],"the":[10,47,79,85,118,138,144,148,155,246],"utilities":[11],"of":[12,87,157],"machine":[13,37],"learning":[14,24],"and":[15,34,50,63,81,182,189,208,227,243],"meeting":[16],"potential":[17],"demands":[18],"for":[19,154,179],"real-world":[20],"applications.":[21],"Deep":[22],"reinforcement":[23],"(DRL)":[25],"is":[26,43,219],"a":[27,133],"key":[28],"component":[29],"realizing":[31],"complex":[32],"decision-making":[33],"control":[35],"by":[36,142,191,236],"learning.":[38],"However,":[39,107],"training":[40,82],"DRL-based":[41],"policies":[42,168],"challenging":[44],"due":[45],"to":[46,59,64,70,94,124,222],"high":[48],"costs":[49],"risks":[51],"associated":[52],"with":[53,55,117,147,225],"interactions":[54],"real":[56],"environments.":[57],"Frameworks":[58],"avoid":[60],"adversarial":[61,88,105,160,247],"vulnerability":[62],"achieve":[65],"robustness":[66,235],"promising":[68],"solutions":[69],"this":[71,129],"problem,":[72],"as":[73,199],"they":[74],"consider":[75],"worst-case":[76],"inputs":[77],"during":[78,162],"evaluation":[80],"phases.":[83],"In":[84,128],"field":[86],"DRL,":[89],"regularization":[90,145],"methods":[91,109,197,229],"known":[93],"be":[95],"effective":[96],"maintaining":[98],"output":[99],"consistency":[100],"even":[101],"when":[102],"suffering":[103],"from":[104],"perturbations.":[106,248],"these":[108],"often":[110],"introduce":[111],"an":[112],"undesired":[113],"bias":[114,140],"that":[115,122,136,215],"conflicts":[116],"original":[119],"DRL":[120,149,196],"objective,":[121],"is,":[123],"maximize":[125],"accumulated":[126],"rewards.":[127],"study,":[130],"we":[131],"propose":[132],"new":[134],"technique":[135,176,218],"mitigates":[137],"undesirable":[139],"effect":[141],"orthogonalizing":[143],"term":[146],"objective.":[150],"This":[151],"approach":[152],"allows":[153],"use":[156],"relatively":[158],"large":[159],"perturbations":[161],"training,":[163],"resulting":[164],"more":[166],"robust":[167],"without":[169],"significant":[170],"computational":[171],"overhead.":[172],"We":[173],"evaluate":[174],"our":[175,216],"on":[177],"benchmarks":[178],"both":[180],"discrete":[181],"continuous":[183],"action":[184],"domains,":[185],"including":[186],"Atari":[187],"2600":[188],"PyBullet,":[190],"integrating":[192],"it":[193],"into":[194],"popular":[195],"such":[198],"Q-network":[201],"(DQN),":[202],"deterministic":[204],"policy":[205],"gradient":[206],"(DDPG),":[207],"soft":[209],"actor-critic":[210],"(SAC).":[211],"The":[212],"results":[213],"demonstrate":[214],"proposed":[217],"either":[220],"superior":[221],"or":[223],"competitive":[224],"baseline":[226],"state-of-the-art":[228],"across":[230],"all":[231],"settings,":[232],"particularly":[233],"improving":[234],"at":[237],"least":[238],"twice":[239],"scores":[240],"DQN":[242],"DDPG":[244],"under":[245]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}