{"id":"https://openalex.org/W2967292964","doi":"https://doi.org/10.1109/icra.2019.8794293","title":"Risk Averse Robust Adversarial Reinforcement Learning","display_name":"Risk Averse Robust Adversarial Reinforcement Learning","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2967292964","doi":"https://doi.org/10.1109/icra.2019.8794293","mag":"2967292964"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2019.8794293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","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/A5065822895","display_name":"Xinlei Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xinlei Pan","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041660944","display_name":"Daniel Seita","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Seita","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013420855","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0001-9328-1611"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089723214","display_name":"John Canny","orcid":"https://orcid.org/0000-0002-7161-7927"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Canny","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5065822895"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":5.6006,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.96693798,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8522","last_page":"8528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9933000206947327,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9534000158309937,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.8757860660552979},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.8582212924957275},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.7366371154785156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7105359435081482},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5941410660743713},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5372713804244995},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5062958002090454},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.489760160446167},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4723673462867737},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44328808784484863},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.2915114164352417},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1553840935230255},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13058775663375854}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8757860660552979},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8582212924957275},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.7366371154785156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7105359435081482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5941410660743713},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5372713804244995},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5062958002090454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.489760160446167},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4723673462867737},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44328808784484863},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2915114164352417},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1553840935230255},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13058775663375854},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2019.8794293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320314637","display_name":"National Physical Science Consortium","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1585575029","https://openalex.org/W1771410628","https://openalex.org/W1945616565","https://openalex.org/W1998534269","https://openalex.org/W2006859604","https://openalex.org/W2145339207","https://openalex.org/W2151237105","https://openalex.org/W2169206416","https://openalex.org/W2257979135","https://openalex.org/W2280163991","https://openalex.org/W2342662072","https://openalex.org/W2356031020","https://openalex.org/W2530849036","https://openalex.org/W2602963933","https://openalex.org/W2605102758","https://openalex.org/W2606508169","https://openalex.org/W2609009256","https://openalex.org/W2619543829","https://openalex.org/W2623491082","https://openalex.org/W2724169821","https://openalex.org/W2727840223","https://openalex.org/W2751973545","https://openalex.org/W2767050701","https://openalex.org/W2773525213","https://openalex.org/W2773691349","https://openalex.org/W2890723163","https://openalex.org/W2962803570","https://openalex.org/W2962872206","https://openalex.org/W2962957005","https://openalex.org/W2962977206","https://openalex.org/W2963024489","https://openalex.org/W2963082979","https://openalex.org/W2963175324","https://openalex.org/W2963207607","https://openalex.org/W2963276097","https://openalex.org/W2963523627","https://openalex.org/W2963637944","https://openalex.org/W2963641140","https://openalex.org/W2963684914","https://openalex.org/W2963713397","https://openalex.org/W2963780574","https://openalex.org/W2963824430","https://openalex.org/W2963826726","https://openalex.org/W2963864421","https://openalex.org/W2963938771","https://openalex.org/W2964061343","https://openalex.org/W2964061993","https://openalex.org/W2964108292","https://openalex.org/W2964121744","https://openalex.org/W2964173023","https://openalex.org/W2964174623","https://openalex.org/W3101442004","https://openalex.org/W3157409643","https://openalex.org/W3162902207","https://openalex.org/W4293545785","https://openalex.org/W4297780563","https://openalex.org/W4297810554","https://openalex.org/W4297824641","https://openalex.org/W4301501993","https://openalex.org/W6631190155","https://openalex.org/W6638018090","https://openalex.org/W6640425456","https://openalex.org/W6682367392","https://openalex.org/W6684921986","https://openalex.org/W6687063787","https://openalex.org/W6692170166","https://openalex.org/W6695011786","https://openalex.org/W6704571135","https://openalex.org/W6706320068","https://openalex.org/W6717230150","https://openalex.org/W6728252718","https://openalex.org/W6735677848","https://openalex.org/W6737893269","https://openalex.org/W6738700159","https://openalex.org/W6739193204","https://openalex.org/W6740092555","https://openalex.org/W6745190604","https://openalex.org/W6745661885","https://openalex.org/W6746443092","https://openalex.org/W6746595151","https://openalex.org/W6747027214"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W4320018150","https://openalex.org/W4239582170","https://openalex.org/W2918664383","https://openalex.org/W106056076","https://openalex.org/W4320855730","https://openalex.org/W2135200719"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,47,70,144],"learning":[2,48,71,145],"has":[3],"recently":[4],"made":[5],"significant":[6],"progress":[7],"in":[8],"solving":[9],"computer":[10],"games":[11],"and":[12,28,81,151,196],"robotic":[13],"control":[14,97],"tasks.":[15],"A":[16,39,88],"known":[17],"problem,":[18],"though,":[19],"is":[20,50,92,99,102,188],"that":[21,93,184],"policies":[22],"overfit":[23],"to":[24,51,171,191,202],"the":[25,44,95,111,116,133,175],"training":[26],"environment":[27],"may":[29],"not":[30,114],"avoid":[31],"rare,":[32],"catastrophic":[33,119],"events":[34,120],"such":[35],"as":[36,174],"automotive":[37],"accidents.":[38],"classical":[40],"technique":[41],"for":[42],"improving":[43],"robustness":[45],"of":[46,56,79,90,108,118,168,177],"algorithms":[49],"train":[52],"on":[53,132,159],"a":[54,85,148,152,160,185,193],"set":[55],"randomized":[57],"environments,":[58],"but":[59],"this":[60,137],"approach":[61,158],"only":[62,94],"guards":[63],"against":[64],"common":[65],"situations.":[66],"Recently,":[67],"robust":[68,142],"adversarial":[69,143],"(RARL)":[72],"was":[73],"developed,":[74],"which":[75],"allows":[76],"efficient":[77],"applications":[78],"random":[80],"systematic":[82],"perturbations":[83],"by":[84],"trained":[86,204],"adversary.":[87,154,207],"limitation":[89],"RARL":[91],"expected":[96,134],"objective":[98],"optimized;":[100],"there":[101],"no":[103],"explicit":[104],"modeling":[105],"or":[106],"optimization":[107],"risk.":[109],"Thus":[110],"agents":[112,203],"do":[113],"consider":[115],"probability":[117],"(i.e.,":[121],"those":[122],"inducing":[123],"abnormally":[124],"large":[125],"negative":[126],"reward),":[127],"except":[128],"through":[129,182],"their":[130],"effect":[131],"objective.":[135],"In":[136],"paper":[138],"we":[139],"introduce":[140],"risk-averse":[141,149,186],"(RARARL),":[146],"using":[147],"protagonist":[150],"risk-seeking":[153,194],"We":[155,164,180],"test":[156],"our":[157],"self-driving":[161],"vehicle":[162],"controller.":[163],"use":[165],"an":[166,206],"ensemble":[167],"policy":[169],"networks":[170],"model":[172],"risk":[173],"variance":[176],"value":[178],"functions.":[179],"show":[181],"experiments":[183],"agent":[187],"better":[189],"equipped":[190],"handle":[192],"adversary,":[195],"experiences":[197],"substantially":[198],"fewer":[199],"crashes":[200],"compared":[201],"without":[205],"Supplementary":[208],"materials":[209],"are":[210],"available":[211],"at":[212],"https://sites.google.com/view/rararl.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}