{"id":"https://openalex.org/W4391022034","doi":"https://doi.org/10.1109/cdc49753.2023.10383252","title":"Initial State Interventions for Deconfounded Imitation Learning","display_name":"Initial State Interventions for Deconfounded Imitation Learning","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391022034","doi":"https://doi.org/10.1109/cdc49753.2023.10383252"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10383252","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc49753.2023.10383252","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":"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/A5072165175","display_name":"Samuel Pfrommer","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":"Samuel Pfrommer","raw_affiliation_strings":["University of California Berkeley,Department of Electrical Engineering and Computer Sciences,Berkeley,CA,94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Berkeley,Department of Electrical Engineering and Computer Sciences,Berkeley,CA,94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011091286","display_name":"Yatong Bai","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":"Yatong Bai","raw_affiliation_strings":["University of California Berkeley,Department of Electrical Engineering and Computer Sciences,Berkeley,CA,94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Berkeley,Department of Electrical Engineering and Computer Sciences,Berkeley,CA,94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069203447","display_name":"Hyunin Lee","orcid":"https://orcid.org/0000-0003-1718-9594"},"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":"Hyunin Lee","raw_affiliation_strings":["University of California Berkeley,Department of Electrical Engineering and Computer Sciences,Berkeley,CA,94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Berkeley,Department of Electrical Engineering and Computer Sciences,Berkeley,CA,94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072786751","display_name":"Somayeh Sojoudi","orcid":"https://orcid.org/0000-0001-7177-7712"},"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":"Somayeh Sojoudi","raw_affiliation_strings":["University of California Berkeley,Department of Electrical Engineering and Computer Sciences,Berkeley,CA,94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Berkeley,Department of Electrical Engineering and Computer Sciences,Berkeley,CA,94720","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19075061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"2312","last_page":"2319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.998199999332428,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9919000267982483,"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/computer-science","display_name":"Computer science","score":0.680450975894928},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5620360970497131},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4732523560523987},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.470798134803772},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.45985111594200134},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4198249578475952},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35008543729782104},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.32812756299972534},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2068997025489807}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.680450975894928},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5620360970497131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4732523560523987},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.470798134803772},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.45985111594200134},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4198249578475952},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35008543729782104},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.32812756299972534},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2068997025489807},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10383252","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc49753.2023.10383252","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":0.75,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2005388202","https://openalex.org/W2070803806","https://openalex.org/W2091565802","https://openalex.org/W2103254706","https://openalex.org/W2143891888","https://openalex.org/W2194775991","https://openalex.org/W2342840547","https://openalex.org/W2580495915","https://openalex.org/W2767506186","https://openalex.org/W2788862220","https://openalex.org/W2883140436","https://openalex.org/W2947630374","https://openalex.org/W2997054006","https://openalex.org/W2998590388","https://openalex.org/W3098253476","https://openalex.org/W3159659315","https://openalex.org/W3212259443","https://openalex.org/W4283772362","https://openalex.org/W4286899435","https://openalex.org/W4287509240","https://openalex.org/W4287637100","https://openalex.org/W4291960813","https://openalex.org/W4298982457","https://openalex.org/W4302423442","https://openalex.org/W4308609982","https://openalex.org/W6631190155","https://openalex.org/W6640174482","https://openalex.org/W6704559304","https://openalex.org/W6752145142","https://openalex.org/W6780559895","https://openalex.org/W6783911189","https://openalex.org/W6785604037","https://openalex.org/W6803275596","https://openalex.org/W6803470638","https://openalex.org/W6803821237","https://openalex.org/W6810310382","https://openalex.org/W6810709996","https://openalex.org/W6839094154","https://openalex.org/W6846663884"],"related_works":["https://openalex.org/W3081694532","https://openalex.org/W1969211203","https://openalex.org/W1517958729","https://openalex.org/W2092272653","https://openalex.org/W1992704972","https://openalex.org/W271627879","https://openalex.org/W2349444258","https://openalex.org/W2062195135","https://openalex.org/W1985388337","https://openalex.org/W4290729391"],"abstract_inverted_index":{"Imitation":[0],"learning":[1],"suffers":[2],"from":[3],"causal":[4,83],"confusion.":[5],"This":[6],"phenomenon":[7],"occurs":[8],"when":[9],"learned":[10],"policies":[11],"attend":[12],"to":[13,66,119,129],"features":[14],"that":[15,92,100,107],"do":[16],"not":[17,103],"causally":[18,108],"influence":[19,109],"the":[20,44,55,63,69,98,110,115],"expert":[21,77,79],"actions":[22],"but":[23,36],"are":[24],"instead":[25],"spuriously":[26],"correlated.":[27],"Causally":[28],"confused":[29],"agents":[30],"produce":[31],"low":[32],"open-loop":[33],"supervised":[34],"loss":[35],"poor":[37],"closed-loop":[38],"performance":[39],"upon":[40],"deployment.":[41],"We":[42],"consider":[43],"problem":[45],"of":[46,54],"masking":[47,60,125],"ob-served":[48],"confounders":[49],"in":[50,68,97],"a":[51],"disentangled":[52],"representation":[53],"observation":[56],"space.":[57],"Our":[58],"novel":[59],"algorithm":[61,94,126],"leverages":[62],"usual":[64],"ability":[65],"intervene":[67],"initial":[70,116],"system":[71],"state,":[72],"avoiding":[73],"any":[74],"requirement":[75],"involving":[76],"querying,":[78],"reward":[80],"functions,":[81],"or":[82],"graph":[84],"specification.":[85],"Under":[86],"certain":[87],"assumptions,":[88],"we":[89],"theoretically":[90],"prove":[91],"this":[93],"is":[95,127],"conservative":[96],"sense":[99],"it":[101],"does":[102],"incorrectly":[104],"mask":[105],"observations":[106],"expert;":[111],"furthermore,":[112],"intervening":[113],"on":[114],"state":[117],"serves":[118],"strictly":[120],"reduce":[121],"excess":[122],"conservatism.":[123],"The":[124],"applied":[128],"behavior":[130],"cloning":[131],"for":[132],"two":[133],"illustrative":[134],"control":[135],"systems:":[136],"CartPole":[137],"and":[138],"Reacher.":[139]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
