{"id":"https://openalex.org/W4391020543","doi":"https://doi.org/10.1109/cdc49753.2023.10383976","title":"Distributionally Robust Behavioral Cloning for Robust Imitation Learning","display_name":"Distributionally Robust Behavioral Cloning for Robust Imitation Learning","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391020543","doi":"https://doi.org/10.1109/cdc49753.2023.10383976"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10383976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383976","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd 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/A5005536479","display_name":"Kishan Panaganti","orcid":"https://orcid.org/0000-0001-9746-698X"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kishan Panaganti","raw_affiliation_strings":["Texas A&M University,Department of Electrical and Computer Engineering,College Station,TX,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University,Department of Electrical and Computer Engineering,College Station,TX,USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101743853","display_name":"Zaiyan Xu","orcid":"https://orcid.org/0000-0001-6194-912X"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zaiyan Xu","raw_affiliation_strings":["Texas A&M University,Department of Electrical and Computer Engineering,College Station,TX,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University,Department of Electrical and Computer Engineering,College Station,TX,USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053096993","display_name":"Dileep Kalathil","orcid":"https://orcid.org/0000-0001-7968-5185"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dileep Kalathil","raw_affiliation_strings":["Texas A&M University,Department of Electrical and Computer Engineering,College Station,TX,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University,Department of Electrical and Computer Engineering,College Station,TX,USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013843778","display_name":"Mohammad Ghavamzadeh","orcid":"https://orcid.org/0000-0003-0930-8688"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Ghavamzadeh","raw_affiliation_strings":["Google Research,USA","Google Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2178,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5038414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1342","last_page":"1347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T10462","display_name":"Reinforcement Learning in Robotics","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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9602000117301941,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9521999955177307,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7583019733428955},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.719050407409668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6107938289642334},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5984079837799072},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.513039231300354},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5087183117866516},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5050638318061829},{"id":"https://openalex.org/keywords/robust-optimization","display_name":"Robust optimization","score":0.4947947859764099},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.48868635296821594},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4465025067329407},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4459651708602905},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4274345338344574},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.4242561459541321},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15149450302124023},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.13502079248428345},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13466838002204895}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7583019733428955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.719050407409668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6107938289642334},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5984079837799072},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.513039231300354},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5087183117866516},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5050638318061829},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.4947947859764099},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.48868635296821594},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4465025067329407},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4459651708602905},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4274345338344574},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.4242561459541321},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15149450302124023},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.13502079248428345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13466838002204895},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10383976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383976","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1057716383","display_name":null,"funder_award_id":"NSF-CAREER-EPCN-2045783,NSF-CNS 1955696","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":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1522301498","https://openalex.org/W1542523037","https://openalex.org/W1965878388","https://openalex.org/W1994530392","https://openalex.org/W2115872032","https://openalex.org/W2152790647","https://openalex.org/W2155153696","https://openalex.org/W2158782408","https://openalex.org/W2168565265","https://openalex.org/W2174803659","https://openalex.org/W2336156739","https://openalex.org/W2537619949","https://openalex.org/W2553297237","https://openalex.org/W2564590721","https://openalex.org/W2604738573","https://openalex.org/W2605102758","https://openalex.org/W2766966154","https://openalex.org/W2767050701","https://openalex.org/W2916286980","https://openalex.org/W2951714068","https://openalex.org/W2962850106","https://openalex.org/W2963277051","https://openalex.org/W2964248288","https://openalex.org/W2990138404","https://openalex.org/W3085800879","https://openalex.org/W3086417465","https://openalex.org/W3093887912","https://openalex.org/W3101442004","https://openalex.org/W3103360925","https://openalex.org/W3117945981","https://openalex.org/W3156216502","https://openalex.org/W3188960136","https://openalex.org/W3212208883","https://openalex.org/W3213249234","https://openalex.org/W3214274533","https://openalex.org/W4206328009","https://openalex.org/W4206797753","https://openalex.org/W4310895557","https://openalex.org/W4312072405","https://openalex.org/W6640174482","https://openalex.org/W6680724558","https://openalex.org/W6684338915","https://openalex.org/W6718092244","https://openalex.org/W6730898090","https://openalex.org/W6748839928","https://openalex.org/W6771312369","https://openalex.org/W6784114448","https://openalex.org/W6784678651","https://openalex.org/W6790447269","https://openalex.org/W6802038118","https://openalex.org/W6803469586","https://openalex.org/W6803692702","https://openalex.org/W6804712669","https://openalex.org/W6841991137","https://openalex.org/W6850327040","https://openalex.org/W7005955626"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2728757335"],"abstract_inverted_index":{"Robust":[0],"reinforcement":[1],"learning":[2,43,108],"(RL)":[3],"aims":[4],"to":[5,24,57,114,165],"learn":[6],"a":[7,47,80,89,106,111],"policy":[8],"that":[9,62,129],"can":[10,63],"withstand":[11,64],"uncertainties":[12,65,149],"in":[13,19,27,30,46,66,151,154],"model":[14,67,167],"parameters,":[15],"which":[16],"often":[17],"arise":[18],"practical":[20],"RL":[21],"applications":[22],"due":[23],"modeling":[25],"errors":[26],"simulators,":[28],"variations":[29],"real-world":[31],"system":[32],"dynamics,":[33,92],"and":[34,142,153],"adversarial":[35],"disturbances.":[36],"This":[37],"paper":[38],"introduces":[39],"the":[40,86,97,101,116,125,139,159],"robust":[41,126,132,145],"imitation":[42],"(IL)":[44],"problem":[45,128],"Markov":[48],"decision":[49],"process":[50],"(MDP)":[51],"framework":[52],"where":[53],"an":[54,59,122],"agent":[55,75],"learns":[56],"mimic":[58],"expert":[60,87],"demonstrator":[61],"parameters":[68],"without":[69,93],"additional":[70],"online":[71],"environment":[72],"interactions.":[73],"The":[74],"is":[76,110],"only":[77],"provided":[78],"with":[79,135],"dataset":[81],"of":[82,162],"state-action":[83],"pairs":[84],"from":[85,100],"on":[88,169],"single":[90],"(nominal)":[91],"any":[94],"information":[95],"about":[96],"true":[98],"rewards":[99],"environment.":[102],"Behavioral":[103],"cloning":[104],"(BC),":[105],"supervised":[107],"method,":[109],"powerful":[112],"algorithm":[113,123,140],"address":[115],"vanilla":[117],"IL":[118,127],"problem.":[119],"We":[120,137,156],"propose":[121],"for":[124],"utilizes":[130],"distributionally":[131],"optimization":[133],"(DRO)":[134],"BC.":[136],"call":[138],"DR-BC":[141],"show":[143],"its":[144],"performance":[146,161],"against":[147],"parameter":[148],"both":[150],"theory":[152],"practice.":[155],"also":[157],"demonstrate":[158],"empirical":[160],"our":[163],"approach":[164],"addressing":[166],"perturbations":[168],"several":[170],"MuJoCo":[171],"continuous":[172],"control":[173],"tasks.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}