{"id":"https://openalex.org/W3144127138","doi":"https://doi.org/10.1109/lra.2021.3068912","title":"Learning From Imperfect Demonstrations From Agents With Varying Dynamics","display_name":"Learning From Imperfect Demonstrations From Agents With Varying Dynamics","publication_year":2021,"publication_date":"2021-03-25","ids":{"openalex":"https://openalex.org/W3144127138","doi":"https://doi.org/10.1109/lra.2021.3068912","mag":"3144127138"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2021.3068912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3068912","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5010800424","display_name":"Zhangjie Cao","orcid":"https://orcid.org/0000-0001-5098-2194"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhangjie Cao","raw_affiliation_strings":["Department of Computer Science, Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5098-2194","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080725225","display_name":"Dorsa Sadigh","orcid":"https://orcid.org/0000-0002-7802-9183"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dorsa Sadigh","raw_affiliation_strings":["Department of Computer Science, Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7802-9183","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.3004,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.83484523,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"6","issue":"3","first_page":"5231","last_page":"5238"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9898999929428101,"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/imitation","display_name":"Imitation","score":0.7789701223373413},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6995673775672913},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.6521509885787964},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.6386743783950806},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6279997825622559},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.6264710426330566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5557929277420044},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5344853401184082},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5123711824417114},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45793843269348145},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10658836364746094},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.08565711975097656},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06917735934257507}],"concepts":[{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7789701223373413},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995673775672913},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.6521509885787964},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6386743783950806},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6279997825622559},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.6264710426330566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5557929277420044},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5344853401184082},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5123711824417114},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45793843269348145},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10658836364746094},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.08565711975097656},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06917735934257507},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/lra.2021.3068912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2021.3068912","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6822619018","display_name":null,"funder_award_id":"1849952","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W112537198","https://openalex.org/W187005120","https://openalex.org/W1510672157","https://openalex.org/W1771410628","https://openalex.org/W1931877416","https://openalex.org/W1986014385","https://openalex.org/W1999874108","https://openalex.org/W2061562262","https://openalex.org/W2098774185","https://openalex.org/W2106338164","https://openalex.org/W2128677288","https://openalex.org/W2142641780","https://openalex.org/W2158349948","https://openalex.org/W2158782408","https://openalex.org/W2171054284","https://openalex.org/W2171425630","https://openalex.org/W2174803659","https://openalex.org/W2750875954","https://openalex.org/W2884247313","https://openalex.org/W2946160813","https://openalex.org/W2949696506","https://openalex.org/W2949916679","https://openalex.org/W2962787969","https://openalex.org/W2962894046","https://openalex.org/W2962957031","https://openalex.org/W2962986791","https://openalex.org/W2963277051","https://openalex.org/W2963508354","https://openalex.org/W2963725546","https://openalex.org/W2963817681","https://openalex.org/W2964120017","https://openalex.org/W2989696291","https://openalex.org/W2992689132","https://openalex.org/W2996076371","https://openalex.org/W3015024584","https://openalex.org/W3035366536","https://openalex.org/W3040033967","https://openalex.org/W3090359064","https://openalex.org/W3104248506","https://openalex.org/W3182474098","https://openalex.org/W4287999668","https://openalex.org/W4289543323","https://openalex.org/W6638018090","https://openalex.org/W6640174482","https://openalex.org/W6674884181","https://openalex.org/W6680724558","https://openalex.org/W6685664872","https://openalex.org/W6718092244","https://openalex.org/W6743636021","https://openalex.org/W6753770476","https://openalex.org/W6753870404","https://openalex.org/W6759312711","https://openalex.org/W6763078103","https://openalex.org/W6763184490","https://openalex.org/W6763952582","https://openalex.org/W6770722459","https://openalex.org/W6771446851","https://openalex.org/W6775370270","https://openalex.org/W6779370943","https://openalex.org/W6780559895"],"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/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2892258405","https://openalex.org/W4295135464"],"abstract_inverted_index":{"Imitation":[0],"learning":[1,10,51,93],"enables":[2,92],"robots":[3],"to":[4,15,79],"learn":[5],"from":[6,61,94],"demonstrations.":[7,18,103],"Previous":[8],"imitation":[9,50,87],"algorithms":[11],"usually":[12],"assume":[13],"access":[14],"optimal":[16,33],"expert":[17],"However,":[19],"in":[20,109],"many":[21],"real-world":[22],"applications,":[23],"this":[24],"assumption":[25],"is":[26,85],"limiting.":[27],"Most":[28],"collected":[29],"demonstrations":[30,54],"are":[31,35],"not":[32],"or":[34,58],"produced":[36],"by":[37],"an":[38,76],"agent":[39],"with":[40,63,120],"slightly":[41],"different":[42],"dynamics.":[43,65],"We":[44,66],"therefore":[45],"address":[46],"the":[47,53,100],"problem":[48],"of":[49,71],"when":[52],"can":[55],"be":[56,59],"sub-optimal":[57],"drawn":[60],"agents":[62],"varying":[64],"develop":[67],"a":[68,72,83,113],"metric":[69],"composed":[70],"feasibility":[73],"score":[74,78,91],"and":[75,98,111],"optimality":[77],"measure":[80],"how":[81],"useful":[82],"demonstration":[84],"for":[86],"learning.":[88],"The":[89],"proposed":[90],"more":[95],"informative":[96],"demonstrations,":[97],"disregarding":[99],"less":[101],"relevant":[102],"Our":[104],"experiments":[105],"on":[106,112],"four":[107],"environments":[108],"simulation":[110],"real":[114],"robot":[115],"show":[116],"improved":[117],"learned":[118],"policies":[119],"higher":[121],"expected":[122],"return.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}