{"id":"https://openalex.org/W3122828824","doi":"https://doi.org/10.1177/0278364920985879","title":"Dynamic regret convergence analysis and an adaptive regularization algorithm for on-policy robot imitation learning","display_name":"Dynamic regret convergence analysis and an adaptive regularization algorithm for on-policy robot imitation learning","publication_year":2021,"publication_date":"2021-01-24","ids":{"openalex":"https://openalex.org/W3122828824","doi":"https://doi.org/10.1177/0278364920985879","mag":"3122828824"},"language":"en","primary_location":{"id":"doi:10.1177/0278364920985879","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0278364920985879","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","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/A5100348028","display_name":"Jonathan Lee","orcid":"https://orcid.org/0000-0002-1828-1707"},"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":true,"raw_author_name":"Jonathan N. Lee","raw_affiliation_strings":["The AUTOLab, University of California, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"The AUTOLab, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052716347","display_name":"Michael Laskey","orcid":null},"institutions":[{"id":"https://openalex.org/I917207718","display_name":"Toyota Industries (United States)","ror":"https://ror.org/0132ebr60","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4210145315","https://openalex.org/I917207718"]},{"id":"https://openalex.org/I4391768151","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108","country_code":null,"type":"facility","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4391768151"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Laskey","raw_affiliation_strings":["Toyota Research Institute, Los Altos, CA, USA"],"affiliations":[{"raw_affiliation_string":"Toyota Research Institute, Los Altos, CA, USA","institution_ids":["https://openalex.org/I917207718","https://openalex.org/I4391768151"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088063475","display_name":"Ajay Kumar Tanwani","orcid":"https://orcid.org/0000-0002-6365-8315"},"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":"Ajay Kumar Tanwani","raw_affiliation_strings":["The AUTOLab, University of California, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"The AUTOLab, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014893911","display_name":"Anil Aswani","orcid":"https://orcid.org/0000-0001-5777-7185"},"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":"Anil Aswani","raw_affiliation_strings":["Department of Industrial Engineering and Operations Research, University of California, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Operations Research, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050342525","display_name":"Ken Goldberg","orcid":"https://orcid.org/0000-0002-2661-4524"},"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":"Ken Goldberg","raw_affiliation_strings":["The AUTOLab, University of California, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"The AUTOLab, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100348028"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.3486,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59807446,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"40","issue":"10-11","first_page":"1284","last_page":"1305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"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/T10603","display_name":"Smart Grid Energy Management","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/regret","display_name":"Regret","score":0.7175508737564087},{"id":"https://openalex.org/keywords/supervisor","display_name":"Supervisor","score":0.6293364763259888},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5962100028991699},{"id":"https://openalex.org/keywords/corrective-feedback","display_name":"Corrective feedback","score":0.5685290098190308},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4719870686531067},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.45809465646743774},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.45295464992523193},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4470401704311371},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.44645723700523376},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.42785072326660156},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.39756786823272705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38410890102386475},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2615397572517395},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2192465364933014},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.09675127267837524},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.0913764238357544},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08365190029144287}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7175508737564087},{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.6293364763259888},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5962100028991699},{"id":"https://openalex.org/C2779305910","wikidata":"https://www.wikidata.org/wiki/Q5172809","display_name":"Corrective feedback","level":2,"score":0.5685290098190308},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4719870686531067},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.45809465646743774},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45295464992523193},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4470401704311371},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.44645723700523376},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.42785072326660156},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.39756786823272705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38410890102386475},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2615397572517395},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2192465364933014},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.09675127267837524},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.0913764238357544},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08365190029144287},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/0278364920985879","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0278364920985879","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1513325188","display_name":null,"funder_award_id":"1734633","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"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320307760","display_name":"Hewlett-Packard Development Company","ror":"https://ror.org/059rn9488"},{"id":"https://openalex.org/F4320307981","display_name":"American Honda Motor","ror":"https://ror.org/04vdmc602"},{"id":"https://openalex.org/F4320308308","display_name":"Siemens Foundation","ror":"https://ror.org/04axb7e79"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320315934","display_name":"Toyota Research Institute","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1458771408","https://openalex.org/W1543439990","https://openalex.org/W1564612581","https://openalex.org/W1570963478","https://openalex.org/W1737105075","https://openalex.org/W1979289676","https://openalex.org/W1980969546","https://openalex.org/W2046637502","https://openalex.org/W2046859786","https://openalex.org/W2064778949","https://openalex.org/W2129160848","https://openalex.org/W2146502635","https://openalex.org/W2154682027","https://openalex.org/W2167224731","https://openalex.org/W2399331166","https://openalex.org/W2527925052","https://openalex.org/W2560674852","https://openalex.org/W2597289420","https://openalex.org/W2604173613","https://openalex.org/W2604272474","https://openalex.org/W2612690371","https://openalex.org/W2767506186","https://openalex.org/W2806163172","https://openalex.org/W2903459254","https://openalex.org/W2963669336","https://openalex.org/W2964309292","https://openalex.org/W3101780148","https://openalex.org/W4205841652","https://openalex.org/W4244364296","https://openalex.org/W4252959020"],"related_works":["https://openalex.org/W4376155396","https://openalex.org/W2971351794","https://openalex.org/W1947085858","https://openalex.org/W2101991911","https://openalex.org/W4390193239","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W4292701710"],"abstract_inverted_index":{"On-policy":[0],"imitation":[1,209],"learning":[2],"algorithms":[3],"such":[4],"as":[5,188],"DAgger":[6,101],"evolve":[7],"a":[8,22,37,49,86,103,155],"robot":[9,190],"control":[10],"policy":[11],"by":[12],"executing":[13],"it,":[14],"measuring":[15],"performance":[16],"(loss),":[17],"obtaining":[18],"corrective":[19],"feedback":[20],"from":[21,128],"supervisor,":[23],"and":[24,134,150,175,186],"generating":[25],"the":[26,30,55,77,89,107,112,129,164,189,193,196,201],"next":[27],"policy.":[28,51,90],"As":[29],"loss":[31],"between":[32],"iterations":[33],"can":[34,139,181],"vary":[35],"unpredictably,":[36],"fundamental":[38],"question":[39],"is":[40,59,63,81,85,95,115,200],"under":[41],"what":[42],"conditions":[43,165],"this":[44,118,122,199],"process":[45],"will":[46],"eventually":[47],"achieve":[48],"converged":[50],"If":[52],"one":[53],"assumes":[54],"underlying":[56,78],"trajectory":[57,79,113],"distribution":[58,80],"static":[60],"(stationary),":[61],"it":[62,84,94],"possible":[64,96],"to":[65,97,142,146,208],"prove":[66,98],"convergence":[67,99,149],"for":[68,75,166],"DAgger.":[69],"However,":[70],"in":[71],"more":[72],"realistic":[73],"models":[74],"robotics,":[76],"dynamic":[82,125,137,184,205],"because":[83],"function":[87],"of":[88,100,109,111,131,195,204],"Recent":[91],"results":[92,153,171],"show":[93,135],"when":[102],"regularity":[104],"condition":[105],"on":[106],"rate":[108],"change":[110],"distributions":[114],"satisfied.":[116],"In":[117],"article,":[119],"we":[120],"reframe":[121],"result":[123],"using":[124],"regret":[126,138,185,206],"theory":[127,207],"field":[130],"online":[132],"optimization":[133],"that":[136,162,178],"be":[140],"applied":[141],"any":[143],"on-policy":[144],"algorithm":[145],"analyze":[147],"its":[148],"optimality.":[151],"These":[152],"inspire":[154],"new":[156],"algorithm,":[157],"Adaptive":[158],"On-Policy":[159],"Regularization":[160],"(Aor),":[161],"ensures":[163],"convergence.":[167],"We":[168],"present":[169],"simulation":[170],"with":[172],"cart\u2013pole":[173],"balancing":[174],"locomotion":[176],"benchmarks":[177],"suggest":[179],"Aor":[180],"significantly":[182],"decrease":[183],"chattering":[187],"learns.":[191],"To":[192],"best":[194],"authors\u2019":[197],"knowledge,":[198],"first":[202],"application":[203],"learning.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}