{"id":"https://openalex.org/W4210444210","doi":"https://doi.org/10.1109/cdc45484.2021.9683559","title":"Adversarial Attacks on Computation of the Modified Policy Iteration Method","display_name":"Adversarial Attacks on Computation of the Modified Policy Iteration Method","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W4210444210","doi":"https://doi.org/10.1109/cdc45484.2021.9683559"},"language":"en","primary_location":{"id":"doi:10.1109/cdc45484.2021.9683559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683559","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5046543057","display_name":"Ali Yekkehkhany","orcid":"https://orcid.org/0000-0001-9130-9668"},"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":"Ali Yekkehkhany","raw_affiliation_strings":["University of California,Department of Industrial Engineering and Operations Research,Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Industrial Engineering and Operations Research,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083194913","display_name":"Feng Han","orcid":"https://orcid.org/0000-0003-2933-6205"},"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":"Han Feng","raw_affiliation_strings":["University of California,Department of Industrial Engineering and Operations Research,Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Industrial Engineering and Operations Research,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042580848","display_name":"Javad Lavaei","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":"Javad Lavaei","raw_affiliation_strings":["University of California,Department of Industrial Engineering and Operations Research,Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Industrial Engineering and Operations Research,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"49","last_page":"56"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.987500011920929,"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/markov-decision-process","display_name":"Markov decision process","score":0.8071101903915405},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7661851644515991},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7156747579574585},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6154964566230774},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5756560564041138},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5634795427322388},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5530850291252136},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41531795263290405},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33371078968048096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3076947331428528},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.30016326904296875},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2275782823562622},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2259267270565033}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8071101903915405},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7661851644515991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7156747579574585},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6154964566230774},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5756560564041138},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5634795427322388},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5530850291252136},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41531795263290405},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33371078968048096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3076947331428528},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.30016326904296875},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2275782823562622},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2259267270565033},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc45484.2021.9683559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683559","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W368265031","https://openalex.org/W1458771408","https://openalex.org/W1512407760","https://openalex.org/W1626155273","https://openalex.org/W1714211023","https://openalex.org/W1945616565","https://openalex.org/W2098432798","https://openalex.org/W2126316555","https://openalex.org/W2134932665","https://openalex.org/W2169982856","https://openalex.org/W2506654222","https://openalex.org/W2556227473","https://openalex.org/W2568772110","https://openalex.org/W2583993537","https://openalex.org/W2594560857","https://openalex.org/W2602963933","https://openalex.org/W2603959005","https://openalex.org/W2609207095","https://openalex.org/W2762403641","https://openalex.org/W2773525213","https://openalex.org/W2773691349","https://openalex.org/W2786070938","https://openalex.org/W2897889564","https://openalex.org/W2904730732","https://openalex.org/W2921860483","https://openalex.org/W2941205169","https://openalex.org/W2950963126","https://openalex.org/W2951187092","https://openalex.org/W2963508354","https://openalex.org/W2963684914","https://openalex.org/W2964061343","https://openalex.org/W2967292964","https://openalex.org/W2982913475","https://openalex.org/W2990887689","https://openalex.org/W3041283756","https://openalex.org/W3081103181","https://openalex.org/W3091226474","https://openalex.org/W3095509234","https://openalex.org/W3100944043","https://openalex.org/W3112248992","https://openalex.org/W3112804989","https://openalex.org/W3127047144","https://openalex.org/W3162902207","https://openalex.org/W4237848379","https://openalex.org/W4250961344","https://openalex.org/W4287635764","https://openalex.org/W4287726313","https://openalex.org/W4297780563","https://openalex.org/W4298023569","https://openalex.org/W4302608015","https://openalex.org/W4386432199","https://openalex.org/W6637441126","https://openalex.org/W6640425456","https://openalex.org/W6682367392","https://openalex.org/W6687063787","https://openalex.org/W6735677848","https://openalex.org/W6745347688","https://openalex.org/W6747027214","https://openalex.org/W6754151078","https://openalex.org/W6769900959","https://openalex.org/W6780856881","https://openalex.org/W6783848444","https://openalex.org/W6784833035","https://openalex.org/W6849860450"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W830459867"],"abstract_inverted_index":{"Adversarial":[0],"attacks":[1,37,98,109],"on":[2,38,110,218],"Markov":[3],"decision":[4],"processes":[5],"(MDPs)":[6],"and":[7,23,40,57,66],"reinforcement":[8,80],"learning":[9,22],"(RL)":[10],"have":[11],"been":[12],"studied":[13],"in":[14,17,60,99,119,135,149,205],"the":[15,18,47,61,83,90,111,114,121,126,138,143,151,160,171,181,184,191,206,219,225],"literature":[16],"context":[19],"of":[20,35,49,55,63,87,107,113,125,137,142,163,183,193,208,221],"robust":[21],"adversarial":[24,36,97,108],"game":[25],"theory.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30],"introduce":[31],"a":[32,104,132,200,209],"new":[33],"notion":[34],"MDP":[39,56],"RL":[41,58],"computation":[42,54,92,112],"that":[43,167,202],"is":[44,68,129,197,203],"motivated":[45],"by":[46],"emergence":[48],"edge":[50,79,88],"computing.":[51],"The":[52],"large-scale":[53],"models":[59],"form":[62],"value/policy":[64],"iteration":[65,117,175,229],"Q-learning":[67],"being":[69],"offloaded":[70],"from":[71],"agents":[72],"to":[73,78,96,153,180,231],"distributed":[74,85],"servers,":[75],"giving":[76],"rise":[77],"learning.":[81],"By":[82],"inherently":[84],"nature":[86],"RL,":[89],"MDP/RL":[91],"can":[93,147,177],"be":[94],"prone":[95],"different":[100],"forms.":[101],"We":[102,165,212],"analyze":[103],"probabilistic":[105],"model":[106],"modified":[115,173,227],"policy":[116,139,174,186,194,228],"method":[118,176,230],"which":[120,233],"principal":[122],"contraction":[123],"property":[124],"Bellman":[127],"operator":[128],"undermined":[130],"with":[131,187,235],"certain":[133,169],"probability":[134,189],"iterations":[136,196,222],"evaluation":[140,195],"step":[141],"aforementioned":[144],"method.":[145],"This":[146],"result":[148],"luring":[150],"agent":[152],"search":[154],"among":[155],"suboptimal":[156],"policies":[157],"without":[158],"improving":[159],"true":[161],"values":[162],"policies.":[164],"prove":[166],"under":[168],"conditions,":[170],"attacked":[172,226],"still":[178],"converge":[179],"vicinity":[182],"optimal":[185],"high":[188],"if":[190],"number":[192,220],"larger":[198],"than":[199],"threshold":[201],"logarithmic":[204],"inverse":[207],"desired":[210],"precision.":[211],"also":[213],"provide":[214],"an":[215,236],"upper":[216],"bound":[217],"needed":[223],"for":[224],"terminate,":[232],"holds":[234],"associated":[237],"confidence":[238],"level.":[239]},"counts_by_year":[{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}