{"id":"https://openalex.org/W3178520484","doi":"https://doi.org/10.1109/tpami.2021.3096966","title":"Error Bounds of Imitating Policies and Environments for Reinforcement Learning","display_name":"Error Bounds of Imitating Policies and Environments for Reinforcement Learning","publication_year":2021,"publication_date":"2021-08-19","ids":{"openalex":"https://openalex.org/W3178520484","doi":"https://doi.org/10.1109/tpami.2021.3096966","mag":"3178520484","pmid":"https://pubmed.ncbi.nlm.nih.gov/34260348"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2021.3096966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3096966","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5101860657","display_name":"Tian Xu","orcid":"https://orcid.org/0000-0001-9409-448X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tian Xu","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012372957","display_name":"Ziniu Li","orcid":"https://orcid.org/0000-0003-0449-002X"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziniu Li","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100342263","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0002-1732-9545"},"institutions":[{"id":"https://openalex.org/I4210090512","display_name":"Guangzhou Experimental Station","ror":"https://ror.org/00f2c2516","country_code":"CN","type":"facility","lineage":["https://openalex.org/I107851509","https://openalex.org/I4210090512","https://openalex.org/I4210127390","https://openalex.org/I4210151987"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yu","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","Pazhou Lab, Guangzhou, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Pazhou Lab, Guangzhou, Guangzhou, China","institution_ids":["https://openalex.org/I4210090512"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101860657"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":3.499,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93740362,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"44","issue":"10","first_page":"6968","last_page":"6980"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9937000274658203,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9689000248908997,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.723462700843811},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.680082380771637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6637928485870361},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4246422052383423},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4149349629878998},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33277249336242676},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15589746832847595}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.723462700843811},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.680082380771637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6637928485870361},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4246422052383423},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4149349629878998},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33277249336242676},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15589746832847595},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057766","descriptor_name":"Policy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057766","descriptor_name":"Policy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057766","descriptor_name":"Policy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2021.3096966","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2021.3096966","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:34260348","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34260348","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6299999952316284}],"awards":[{"id":"https://openalex.org/G5469316478","display_name":null,"funder_award_id":"61876077","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1524622012","https://openalex.org/W1538452572","https://openalex.org/W1638306878","https://openalex.org/W1999874108","https://openalex.org/W2051228319","https://openalex.org/W2102847492","https://openalex.org/W2120678009","https://openalex.org/W2131940723","https://openalex.org/W2257979135","https://openalex.org/W2268617045","https://openalex.org/W2296673577","https://openalex.org/W2328111639","https://openalex.org/W2489939061","https://openalex.org/W2540093921","https://openalex.org/W2612281180","https://openalex.org/W2808577099","https://openalex.org/W2877093712","https://openalex.org/W2892806280","https://openalex.org/W2951625652","https://openalex.org/W2962787969","https://openalex.org/W2962894046","https://openalex.org/W2963654596","https://openalex.org/W2989847975","https://openalex.org/W3034545053","https://openalex.org/W3035076526","https://openalex.org/W3103205980","https://openalex.org/W3118210634","https://openalex.org/W3169173405","https://openalex.org/W4214717370","https://openalex.org/W4236362309","https://openalex.org/W4293404332","https://openalex.org/W4298023569","https://openalex.org/W4302366875","https://openalex.org/W6636883245","https://openalex.org/W6638018090","https://openalex.org/W6640174482","https://openalex.org/W6675474052","https://openalex.org/W6676728370","https://openalex.org/W6680724558","https://openalex.org/W6713055699","https://openalex.org/W6717434760","https://openalex.org/W6718092244","https://openalex.org/W6729906282","https://openalex.org/W6734209382","https://openalex.org/W6735913928","https://openalex.org/W6736209634","https://openalex.org/W6739659843","https://openalex.org/W6741832134","https://openalex.org/W6745903366","https://openalex.org/W6747473740","https://openalex.org/W6748519856","https://openalex.org/W6751087324","https://openalex.org/W6753183898","https://openalex.org/W6753985592","https://openalex.org/W6754484421","https://openalex.org/W6764053384","https://openalex.org/W6769977606","https://openalex.org/W6771249860","https://openalex.org/W6771378615","https://openalex.org/W6779386277","https://openalex.org/W6780201113","https://openalex.org/W6780495964","https://openalex.org/W6780559895","https://openalex.org/W6784114448","https://openalex.org/W6785801403","https://openalex.org/W6796210719"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407"],"abstract_inverted_index":{"In":[0,41],"sequential":[1],"decision-making,":[2],"imitation":[3,15,59,74,152,180],"learning":[4,184],"(IL)":[5],"trains":[6],"a":[7,38,109,158,175],"policy":[8,53,159],"efficiently":[9],"by":[10,57,149],"mimicking":[11],"expert":[12,52],"demonstrations.":[13],"Various":[14],"methods":[16],"were":[17],"proposed":[18],"and":[19,54,64,196],"empirically":[20],"evaluated,":[21],"meanwhile,":[22],"their":[23],"theoretical":[24],"understandings":[25],"need":[26],"further":[27,131],"studies,":[28],"among":[29],"which":[30],"the":[31,47,51,77,86,95,104,119,125,133,166,171],"compounding":[32,78],"error":[33,79,161],"in":[34,100,194],"long-horizon":[35],"decisions":[36],"is":[37,163],"major":[39],"issue.":[40],"this":[42],"paper,":[43],"we":[44,84,130,156],"first":[45],"analyze":[46,132],"value":[48],"gap":[49],"between":[50],"imitated":[55,148],"policies":[56],"two":[58,92],"methods,":[60],"behavioral":[61],"cloning":[62],"(BC)":[63],"generative":[65,72,150],"adversarial":[66,73,151,179],"imitation.":[67],"The":[68,138],"results":[69,139,189],"support":[70],"that":[71,141,162],"can":[75,113,144],"reduce":[76],"compared":[80],"to":[81,117],"BC.":[82,154],"Furthermore,":[83],"establish":[85],"lower":[87],"bounds":[88,126],"of":[89,97,127,135,178],"IL":[90,112,195],"under":[91],"settings,":[93],"suggesting":[94,174],"significance":[96],"environment":[98,105,120,142],"interactions":[99],"IL.":[101],"By":[102],"considering":[103],"transition":[106],"model":[107,172],"as":[108],"dual":[110],"agent,":[111],"also":[114],"be":[115,145],"used":[116],"learn":[118],"model.":[121],"Therefore,":[122],"based":[123],"on":[124],"imitating":[128,136],"policies,":[129],"performance":[134],"environments.":[137],"show":[140],"models":[143],"more":[146],"effectively":[147],"than":[153],"Particularly,":[155],"obtain":[157],"evaluation":[160],"linear":[164],"with":[165],"effective":[167],"planning":[168],"horizon":[169],"w.r.t.":[170],"bias,":[173],"novel":[176],"application":[177],"for":[181],"model-based":[182],"reinforcement":[183],"(MBRL).":[185],"We":[186],"hope":[187],"these":[188],"could":[190],"inspire":[191],"future":[192],"advances":[193],"MBRL.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}