{"id":"https://openalex.org/W4312650890","doi":"https://doi.org/10.1109/tg.2022.3224088","title":"Curriculum Goal-Conditioned Imitation for Offline Reinforcement Learning","display_name":"Curriculum Goal-Conditioned Imitation for Offline Reinforcement Learning","publication_year":2022,"publication_date":"2022-11-24","ids":{"openalex":"https://openalex.org/W4312650890","doi":"https://doi.org/10.1109/tg.2022.3224088"},"language":"en","primary_location":{"id":"doi:10.1109/tg.2022.3224088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2022.3224088","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"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 Transactions on Games","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/A5039711250","display_name":"Xiaoyun Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyun Feng","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4131-0625","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044960023","display_name":"Jiang Li","orcid":"https://orcid.org/0000-0002-9856-8002"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Jiang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101412837","display_name":"Xudong Yu","orcid":"https://orcid.org/0000-0001-5720-1215"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Yu","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0001-5720-1215","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101855228","display_name":"Haoran Xu","orcid":"https://orcid.org/0009-0005-2477-5737"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Xu","raw_affiliation_strings":["JD Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Technology, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100656317","display_name":"Xiaoyan Sun","orcid":"https://orcid.org/0000-0003-3638-5566"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Sun","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440022","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0001-8623-4622"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052921346","display_name":"Xianyuan Zhan","orcid":"https://orcid.org/0000-0002-3683-0554"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianyuan Zhan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3683-0554","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053833625","display_name":"Wai Kin Chan","orcid":"https://orcid.org/0000-0002-7202-1922"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wai Kin Chan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7202-1922","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5039711250"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.4162,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69435231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"16","issue":"1","first_page":"102","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9868999719619751,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9739999771118164,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.8009772300720215},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6826037168502808},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.6252186894416809},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5632226467132568},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.5482136607170105},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4889453649520874},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.4762839674949646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4683617353439331},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.20490658283233643},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14800965785980225},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.09752801060676575},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.09530964493751526}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8009772300720215},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6826037168502808},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.6252186894416809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5632226467132568},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.5482136607170105},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4889453649520874},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4762839674949646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4683617353439331},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.20490658283233643},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14800965785980225},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.09752801060676575},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.09530964493751526},{"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/tg.2022.3224088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tg.2022.3224088","pdf_url":null,"source":{"id":"https://openalex.org/S4210224842","display_name":"IEEE Transactions on Games","issn_l":"2475-1502","issn":["2475-1502","2475-1510"],"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 Transactions on Games","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5799999833106995,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2195155527","display_name":null,"funder_award_id":"WDZC20200818121348001","funder_id":"https://openalex.org/F4320326705","funder_display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality"},{"id":"https://openalex.org/G4761585152","display_name":null,"funder_award_id":"JCYJ20210324135011030","funder_id":"https://openalex.org/F4320326705","funder_display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality"},{"id":"https://openalex.org/G6298785130","display_name":null,"funder_award_id":"71971127","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"},{"id":"https://openalex.org/F4320326705","display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W166862392","https://openalex.org/W2043968544","https://openalex.org/W2162704429","https://openalex.org/W2604382266","https://openalex.org/W2902125520","https://openalex.org/W2953981431","https://openalex.org/W2991355586","https://openalex.org/W2997876358","https://openalex.org/W3016525976","https://openalex.org/W3034728521","https://openalex.org/W3097907450","https://openalex.org/W3207335863","https://openalex.org/W4287997992","https://openalex.org/W4287998029","https://openalex.org/W4293872189","https://openalex.org/W6616173779","https://openalex.org/W6635701881","https://openalex.org/W6684338915","https://openalex.org/W6740801417","https://openalex.org/W6747473740","https://openalex.org/W6748012927","https://openalex.org/W6748599296","https://openalex.org/W6748848655","https://openalex.org/W6751540476","https://openalex.org/W6756908582","https://openalex.org/W6757469721","https://openalex.org/W6760439459","https://openalex.org/W6762640273","https://openalex.org/W6763704811","https://openalex.org/W6764173040","https://openalex.org/W6765008394","https://openalex.org/W6767047803","https://openalex.org/W6767246565","https://openalex.org/W6767649332","https://openalex.org/W6769035977","https://openalex.org/W6770887232","https://openalex.org/W6771270455","https://openalex.org/W6771670691","https://openalex.org/W6772111244","https://openalex.org/W6774583691","https://openalex.org/W6776601253","https://openalex.org/W6777091672","https://openalex.org/W6777656069","https://openalex.org/W6779265984","https://openalex.org/W6779366341","https://openalex.org/W6779463497","https://openalex.org/W6785353143","https://openalex.org/W6796289742","https://openalex.org/W6796589144","https://openalex.org/W6801798027","https://openalex.org/W6802659552","https://openalex.org/W6802762872","https://openalex.org/W6804160314","https://openalex.org/W6811554491"],"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/W2665305151"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2,5,109,147],"(RL)":[3],"enables":[4],"policies":[6,37],"from":[7],"precollected":[8],"datasets":[9],"without":[10],"online":[11],"data":[12,70],"collection.":[13],"Although":[14],"it":[15,83],"offers":[16],"the":[17,21,24,53,105,112,150],"possibility":[18],"to":[19,32,43,51,110],"surpass":[20],"performance":[22,169],"of":[23,66,107,124,131],"datasets,":[25],"most":[26],"existing":[27],"offline":[28,100,172],"RL":[29,101,173],"algorithms":[30],"struggle":[31],"compete":[33],"with":[34,179],"behavior":[35],"cloning":[36],"in":[38,69,87,97],"many":[39,58],"dataset":[40],"settings":[41],"due":[42],"trading":[44],"off":[45],"policy":[46,91,146],"improvement":[47],"and":[48,71,136,182],"additional":[49],"regularization":[50],"address":[52],"distributional":[54],"shift":[55],"issue.":[56],"In":[57],"cases,":[59],"if":[60],"one":[61],"can":[62],"imitate":[63],"a":[64,88,117,122,129],"sequence":[65,123],"suboptimal":[67,125,142],"subtrajectories":[68],"properly":[72],"<italic":[73],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[74],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u201cstitch\u201d</i>":[75],"them":[76],"toward":[77,148],"reaching":[78,149],"an":[79],"ideal":[80,151],"future":[81,134],"state,":[82],"may":[84],"potentially":[85],"result":[86],"more":[89],"reliable":[90],"while":[92],"avoiding":[93],"difficulties":[94],"that":[95,119,165],"present":[96],"typical":[98],"value-based":[99],"algorithms.":[102],"We":[103,115,154],"borrow":[104],"idea":[106],"curriculum":[108,118,158],"embody":[111],"above":[113],"intuition.":[114],"construct":[116],"progressively":[120],"imitates":[121],"trajectories":[126,143],"conditioned":[127],"on":[128],"series":[130],"carefully":[132],"constructed":[133],"states":[135],"cumulative":[137],"rewards":[138],"as":[139],"goals.":[140],"The":[141],"gradually":[144],"guide":[145],"goal":[152],"states.":[153],"name":[155],"our":[156],"algorithm":[157],"goal-conditioned":[159],"imitation":[160],"(CGI).":[161],"Experimental":[162],"results":[163],"show":[164],"CGI":[166],"achieves":[167],"competitive":[168],"against":[170],"state-of-the-art":[171],"algorithms,":[174],"especially":[175],"for":[176],"challenging":[177],"tasks":[178],"long":[180],"horizons":[181],"sparse":[183],"rewards.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}