{"id":"https://openalex.org/W4315488785","doi":"https://doi.org/10.1109/cdc51059.2022.9992959","title":"Inverse-Inverse Reinforcement Learning. How to Hide Strategy from an Adversarial Inverse Reinforcement Learner","display_name":"Inverse-Inverse Reinforcement Learning. How to Hide Strategy from an Adversarial Inverse Reinforcement Learner","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315488785","doi":"https://doi.org/10.1109/cdc51059.2022.9992959"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9992959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9992959","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st 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":"2022 IEEE 61st 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/A5084702668","display_name":"Kunal Pattanayak","orcid":"https://orcid.org/0000-0002-6684-4148"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunal Pattanayak","raw_affiliation_strings":["Cornell University,School of Electrical and Computer Engineering,Ithaca,NY,USA,14853"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University,School of Electrical and Computer Engineering,Ithaca,NY,USA,14853","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068804090","display_name":"Vikram Krishnamurthy","orcid":"https://orcid.org/0000-0002-4170-6056"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikram Krishnamurthy","raw_affiliation_strings":["Cornell University,School of Electrical and Computer Engineering,Ithaca,NY,USA,14853"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University,School of Electrical and Computer Engineering,Ithaca,NY,USA,14853","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017310968","display_name":"Christopher Berry","orcid":"https://orcid.org/0000-0002-6054-9180"},"institutions":[{"id":"https://openalex.org/I1287521167","display_name":"Lockheed Martin (United States)","ror":"https://ror.org/026er9r08","country_code":"US","type":"company","lineage":["https://openalex.org/I1287521167"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Berry","raw_affiliation_strings":["Lockheed Martin Advanced Technology Laboratories,Cherry Hill,NJ,USA,08002"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lockheed Martin Advanced Technology Laboratories,Cherry Hill,NJ,USA,08002","institution_ids":["https://openalex.org/I1287521167"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5182,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85656316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3631","last_page":"3636"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9894999861717224,"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":0.9894999861717224,"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":0.9891999959945679,"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/T11513","display_name":"stochastic dynamics and bifurcation","score":0.9772999882698059,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.7278994917869568},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7264231443405151},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6966137886047363},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.663175106048584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5976606011390686},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.5780095458030701},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45985063910484314},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18912354111671448},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13528752326965332},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.0698365867137909},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.05190330743789673}],"concepts":[{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.7278994917869568},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7264231443405151},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6966137886047363},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.663175106048584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5976606011390686},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.5780095458030701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45985063910484314},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18912354111671448},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13528752326965332},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0698365867137909},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.05190330743789673},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc51059.2022.9992959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9992959","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st 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":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.5600000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306994","display_name":"Lockheed Martin","ror":"https://ror.org/026er9r08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1511442893","https://openalex.org/W1588591676","https://openalex.org/W1999874108","https://openalex.org/W2000804318","https://openalex.org/W2004394537","https://openalex.org/W2031483369","https://openalex.org/W2044943815","https://openalex.org/W2063146632","https://openalex.org/W2066533334","https://openalex.org/W2118508075","https://openalex.org/W2133721238","https://openalex.org/W2169498096","https://openalex.org/W2195832715","https://openalex.org/W2221656098","https://openalex.org/W2324700963","https://openalex.org/W2903687574","https://openalex.org/W2909326050","https://openalex.org/W3122344118","https://openalex.org/W3174900691","https://openalex.org/W3176865002","https://openalex.org/W4214717370","https://openalex.org/W4234913304","https://openalex.org/W4287745534","https://openalex.org/W4293094234","https://openalex.org/W6674884181","https://openalex.org/W6780095956","https://openalex.org/W6797478188"],"related_works":["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","https://openalex.org/W2331917905","https://openalex.org/W3155039083"],"abstract_inverted_index":{"Inverse":[0],"reinforcement":[1],"learning":[2],"(IRL)":[3],"deals":[4],"with":[5],"estimating":[6],"an":[7,20,28,55,72,90,174],"agent\u2019s":[8,62,79,84],"utility":[9,85,154],"function":[10],"from":[11],"its":[12,24,44,52,127],"actions.":[13],"In":[14],"this":[15,34],"paper,":[16],"we":[17,32,70,88,134,157],"consider":[18],"how":[19],"agent":[21,119,147],"can":[22],"hide":[23],"strategy":[25,53,80,129],"and":[26],"mitigate":[27,173],"adversarial":[29,73,175],"IRL":[30,36,58,74,96],"attack;":[31],"call":[33],"inverse":[35],"(I-IRL).":[37],"How":[38],"should":[39],"the":[40,61,78,83,95,100,118,146,152],"decision":[41],"maker":[42],"choose":[43,122],"response":[45],"to":[46,59,120,172],"ensure":[47],"a":[48,136,163,167],"poor":[49],"reconstruction":[50],"of":[51,151],"by":[54,99],"adversary":[56],"performing":[57],"estimate":[60],"strategy?":[63],"This":[64],"paper":[65],"comprises":[66],"four":[67],"results:":[68],"First,":[69],"present":[71],"algorithm":[75,97],"that":[76,93,126],"estimates":[77,150],"while":[81],"controlling":[82],"function.":[86,155],"Then,":[87],"propose":[89],"I-IRL":[91,103,143,160],"result":[92,139,144],"mitigates":[94],"used":[98],"adversary.":[101],"Our":[102],"results":[104],"are":[105],"based":[106],"on":[107],"revealed":[108],"preference":[109],"theory":[110],"in":[111,162],"microeconomics.":[112],"The":[113],"key":[114],"idea":[115],"is":[116,130,170],"for":[117,140],"deliberately":[121],"sub-optimal":[123],"responses":[124],"so":[125],"true":[128],"sufficiently":[131],"masked.":[132],"Third,":[133],"give":[135],"sample":[137],"complexity":[138],"our":[141,159],"main":[142],"when":[145],"has":[148],"noisy":[149],"adversary-specified":[153],"Finally,":[156],"illustrate":[158],"scheme":[161],"radar":[164,169],"problem":[165],"where":[166],"meta-cognitive":[168],"trying":[171],"target.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}