{"id":"https://openalex.org/W3043225036","doi":"https://doi.org/10.23919/acc45564.2020.9147846","title":"Robustifying Reinforcement Learning Agents via Action Space Adversarial Training","display_name":"Robustifying Reinforcement Learning Agents via Action Space Adversarial Training","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3043225036","doi":"https://doi.org/10.23919/acc45564.2020.9147846","mag":"3043225036"},"language":"en","primary_location":{"id":"doi:10.23919/acc45564.2020.9147846","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc45564.2020.9147846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.07176","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103068884","display_name":"Kai Liang Tan","orcid":"https://orcid.org/0000-0003-2559-1559"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kai Liang Tan","raw_affiliation_strings":["Dept. of Mechanical Engineering, Iowa State University, Ames, IA","[Department of Mechanical Engineering, Iowa State University, Ames, IA]"],"affiliations":[{"raw_affiliation_string":"Dept. of Mechanical Engineering, Iowa State University, Ames, IA","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"[Department of Mechanical Engineering, Iowa State University, Ames, IA]","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054841636","display_name":"Yasaman Esfandiari","orcid":"https://orcid.org/0000-0002-8178-5385"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yasaman Esfandiari","raw_affiliation_strings":["Dept. of Mechanical Engineering, Iowa State University, Ames, IA","[Department of Mechanical Engineering, Iowa State University, Ames, IA]"],"affiliations":[{"raw_affiliation_string":"Dept. of Mechanical Engineering, Iowa State University, Ames, IA","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"[Department of Mechanical Engineering, Iowa State University, Ames, IA]","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082183525","display_name":"Xian Yeow Lee","orcid":"https://orcid.org/0000-0001-6639-8398"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xian Yeow Lee","raw_affiliation_strings":["Dept. of Mechanical Engineering, Iowa State University, Ames, IA","[Department of Mechanical Engineering, Iowa State University, Ames, IA]"],"affiliations":[{"raw_affiliation_string":"Dept. of Mechanical Engineering, Iowa State University, Ames, IA","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"[Department of Mechanical Engineering, Iowa State University, Ames, IA]","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084280568","display_name":"Aakanksha Aakanksha","orcid":null},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aakanksha","raw_affiliation_strings":["Dept. of Mechanical Engineering, Iowa State University, Ames, IA","[Department of Mechanical Engineering, Iowa State University, Ames, IA]"],"affiliations":[{"raw_affiliation_string":"Dept. of Mechanical Engineering, Iowa State University, Ames, IA","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"[Department of Mechanical Engineering, Iowa State University, Ames, IA]","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081037761","display_name":"Soumik Sarkar","orcid":"https://orcid.org/0000-0002-6775-9199"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumik Sarkar","raw_affiliation_strings":["Dept. of Mechanical Engineering, Iowa State University, Ames, IA","[Department of Mechanical Engineering, Iowa State University, Ames, IA]"],"affiliations":[{"raw_affiliation_string":"Dept. of Mechanical Engineering, Iowa State University, Ames, IA","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"[Department of Mechanical Engineering, Iowa State University, Ames, IA]","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103068884"],"corresponding_institution_ids":["https://openalex.org/I173911158"],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64005477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3959","last_page":"3964"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9997000098228455,"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":0.9997000098228455,"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.9945999979972839,"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"}},{"id":"https://openalex.org/T12495","display_name":"Electrostatic Discharge in Electronics","score":0.9610000252723694,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.8573541045188904},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.8531510829925537},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6805455088615417},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5081279277801514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4977107346057892},{"id":"https://openalex.org/keywords/cyber-physical-system","display_name":"Cyber-physical system","score":0.49295687675476074},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4703179895877838},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.46857357025146484},{"id":"https://openalex.org/keywords/actuator","display_name":"Actuator","score":0.4382944405078888},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4311991333961487},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42562878131866455},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.35959649085998535},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.35497963428497314},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.3361101448535919},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1906318962574005}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8573541045188904},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8531510829925537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6805455088615417},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5081279277801514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4977107346057892},{"id":"https://openalex.org/C179768478","wikidata":"https://www.wikidata.org/wiki/Q1120057","display_name":"Cyber-physical system","level":2,"score":0.49295687675476074},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4703179895877838},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.46857357025146484},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.4382944405078888},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4311991333961487},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42562878131866455},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.35959649085998535},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.35497963428497314},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3361101448535919},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1906318962574005},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.23919/acc45564.2020.9147846","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc45564.2020.9147846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 American Control Conference (ACC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2007.07176","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.07176","pdf_url":"https://arxiv.org/pdf/2007.07176","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3043225036","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2007.07176","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2007.07176","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.07176","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.07176","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.07176","pdf_url":"https://arxiv.org/pdf/2007.07176","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G2023424935","display_name":null,"funder_award_id":"CNS-1845969","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7305207087","display_name":null,"funder_award_id":"1845969","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3043225036.pdf","grobid_xml":"https://content.openalex.org/works/W3043225036.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W9657784","https://openalex.org/W1771410628","https://openalex.org/W1883420340","https://openalex.org/W1998602421","https://openalex.org/W2005895359","https://openalex.org/W2062132646","https://openalex.org/W2084793872","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2156737235","https://openalex.org/W2269778407","https://openalex.org/W2320262435","https://openalex.org/W2568356656","https://openalex.org/W2602963933","https://openalex.org/W2603766943","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2773691349","https://openalex.org/W2782165945","https://openalex.org/W2788820894","https://openalex.org/W2794861414","https://openalex.org/W2883567023","https://openalex.org/W2890141553","https://openalex.org/W2913266441","https://openalex.org/W2913552006","https://openalex.org/W2914994663","https://openalex.org/W2962755762","https://openalex.org/W2963207607","https://openalex.org/W2963389226","https://openalex.org/W2963784236","https://openalex.org/W2963857521","https://openalex.org/W2964082701","https://openalex.org/W2964108292","https://openalex.org/W2964153729","https://openalex.org/W2964253222","https://openalex.org/W2971646738","https://openalex.org/W2980360016","https://openalex.org/W2990586332","https://openalex.org/W3103836116","https://openalex.org/W3195133498","https://openalex.org/W6637162671","https://openalex.org/W6638018090","https://openalex.org/W6639568328","https://openalex.org/W6640425456","https://openalex.org/W6683195989","https://openalex.org/W6711870810","https://openalex.org/W6729756640","https://openalex.org/W6735677848","https://openalex.org/W6739868092","https://openalex.org/W6741002519","https://openalex.org/W6747027214","https://openalex.org/W6748007327","https://openalex.org/W6748982675","https://openalex.org/W6753570253","https://openalex.org/W6754447547","https://openalex.org/W6759129252","https://openalex.org/W6759312646","https://openalex.org/W6767061939","https://openalex.org/W6769306871","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3200885897","https://openalex.org/W3083428176","https://openalex.org/W3207613384","https://openalex.org/W3015490850","https://openalex.org/W2969864365","https://openalex.org/W3032638893","https://openalex.org/W2982569142","https://openalex.org/W2953920146","https://openalex.org/W3158507034","https://openalex.org/W2900156534","https://openalex.org/W2985020889","https://openalex.org/W3031351653","https://openalex.org/W2964272011","https://openalex.org/W2923778952","https://openalex.org/W3200724328","https://openalex.org/W2946344298","https://openalex.org/W3025279871","https://openalex.org/W2973930634","https://openalex.org/W2887432790","https://openalex.org/W3210539494"],"abstract_inverted_index":{"Adoption":[0],"of":[1,14,39,58,128,148],"machine":[2],"learning":[3,29],"(ML)-enabled":[4],"cyber-physical":[5],"systems":[6,49,60,69],"(CPS)":[7],"are":[8,174],"becoming":[9],"prevalent":[10],"in":[11,26,35,85,107],"various":[12],"sectors":[13],"modern":[15],"society":[16],"such":[17],"as":[18],"transportation,":[19],"industrial,":[20],"and":[21,42,64,143,157,161],"power":[22],"grids.":[23],"Recent":[24],"studies":[25],"deep":[27],"reinforcement":[28],"(DRL)":[30],"have":[31],"demonstrated":[32,140],"its":[33,141],"benefits":[34],"a":[36,88,97,101,111,125,186],"large":[37],"variety":[38],"data-driven":[40],"decisions":[41],"control":[43,68,123,162,172],"applications.":[44],"As":[45],"reliance":[46],"on":[47,154,159],"ML-enabled":[48],"grows,":[50],"it":[51],"is":[52,104,113,132,191],"imperative":[53],"to":[54,95,118,177,194],"study":[55],"the":[56,79,146,165],"performance":[57],"these":[59,75,108],"under":[61],"malicious":[62],"state":[63],"actuator":[65,199],"attacks.":[66,120,179],"Traditional":[67],"employ":[70],"resilient/fault-tolerant":[71],"controllers":[72],"that":[73,137,185,190],"counter":[74],"attacks":[76],"by":[77],"correcting":[78],"system":[80,112],"via":[81],"error":[82],"observations.":[83],"However,":[84,145],"some":[86],"applications,":[87],"resilient":[89],"controller":[90],"may":[91],"not":[92,158],"be":[93,202],"sufficient":[94],"avoid":[96],"catastrophic":[98],"failure.":[99],"Ideally,":[100],"robust":[102,115,122,130,149],"approach":[103],"more":[105],"useful":[106],"scenarios":[109],"where":[110],"inherently":[114],"(by":[116],"design)":[117],"adversarial":[119,178,208],"While":[121],"has":[124,138,152],"long":[126],"history":[127],"development,":[129],"ML":[131,150,166],"an":[133],"emerging":[134],"research":[135,151],"area":[136],"already":[139],"relevance":[142],"urgency.":[144],"majority":[147],"focused":[153],"perception":[155],"tasks":[156],"decision":[160],"tasks,":[163],"although":[164],"(specifically":[167],"RL)":[168],"models":[169],"used":[170],"for":[171],"applications":[173],"equally":[175],"vulnerable":[176],"In":[180],"this":[181],"paper,":[182],"we":[183],"show":[184],"well-performing":[187],"DRL":[188],"agent":[189],"initially":[192],"susceptible":[193],"action":[195],"space":[196],"perturbations":[197,206],"(e.g.":[198],"attacks)":[200],"can":[201],"robustified":[203],"against":[204],"similar":[205],"through":[207],"training.":[209]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
