{"id":"https://openalex.org/W7154191972","doi":"https://doi.org/10.1109/lra.2026.3683594","title":"Self-Evolved Imitation Learning in Simulated World","display_name":"Self-Evolved Imitation Learning in Simulated World","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7154191972","doi":"https://doi.org/10.1109/lra.2026.3683594"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3683594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3683594","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/A5133493109","display_name":"Yifan Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Yifan Ye","raw_affiliation_strings":["College of Science and Engineering, Hamad Bin Khalifa University, Education City, Doha, Qatar"],"raw_orcid":"https://orcid.org/0009-0008-1305-1014","affiliations":[{"raw_affiliation_string":"College of Science and Engineering, Hamad Bin Khalifa University, Education City, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133478327","display_name":"Jun Cen","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Cen","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7578-7667","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Chen","orcid":"https://orcid.org/0000-0001-5206-1110"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Chen","raw_affiliation_strings":["School of Physics and Optoelectric Engineering, Guangdong University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5206-1110","affiliations":[{"raw_affiliation_string":"School of Physics and Optoelectric Engineering, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057760050","display_name":"Zhihe Lu","orcid":"https://orcid.org/0000-0002-6917-8654"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Zhihe Lu","raw_affiliation_strings":["College of Science and Engineering, Hamad Bin Khalifa University, Education City, Doha, Qatar"],"raw_orcid":"https://orcid.org/0000-0002-6917-8654","affiliations":[{"raw_affiliation_string":"College of Science and Engineering, Hamad Bin Khalifa University, Education City, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.4539889,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"6","first_page":"6967","last_page":"6974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.35510000586509705,"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":0.35510000586509705,"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":0.32839998602867126,"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/T12290","display_name":"Human Motion and Animation","score":0.03750000149011612,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.6837000250816345},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.682699978351593},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4404999911785126},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3880000114440918},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.382099986076355},{"id":"https://openalex.org/keywords/learning-curve","display_name":"Learning curve","score":0.35199999809265137},{"id":"https://openalex.org/keywords/learning-object","display_name":"Learning object","score":0.3515999913215637},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.33500000834465027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7067999839782715},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6837000250816345},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.682699978351593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6324999928474426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5527999997138977},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C2779542340","wikidata":"https://www.wikidata.org/wiki/Q1062461","display_name":"Learning object","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C2986563244","wikidata":"https://www.wikidata.org/wiki/Q6822310","display_name":"Learning to learn","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.3084999918937683},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3683594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3683594","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":[],"funders":[{"id":"https://openalex.org/F4320319188","display_name":"Hamad Bin Khalifa University","ror":"https://ror.org/03eyq4y97"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Imitation":[0,37],"learning":[1],"has":[2],"been":[3],"a":[4,9,40,45,110,152],"trend":[5],"recently,":[6],"yet":[7],"training":[8,140],"generalist":[10],"agent":[11],"across":[12],"multiple":[13],"tasks":[14,55],"still":[15],"requires":[16],"large-scale":[17],"expert":[18],"demonstrations,":[19,77],"which":[20,60],"are":[21,63],"costly":[22],"and":[23,97,116],"labor-intensive":[24],"to":[25,91,123,133],"collect.":[26],"To":[27,71],"address":[28],"the":[29,57,73,94,120,131,145],"challenge":[30],"of":[31,75],"limited":[32],"supervision,":[33],"we":[34],"propose":[35],"Self-Evolved":[36],"Learning":[38],"(SEIL),":[39],"framework":[41],"that":[42,113,149],"progressively":[43],"improves":[44],"few-shot":[46,157],"model":[47,52,90,132],"through":[48],"simulator":[49],"interactions.":[50],"The":[51],"first":[53],"attempts":[54],"in":[56,103,156],"simulator,":[58],"from":[59,119],"successful":[61],"trajectories":[62,118],"collected":[64],"as":[65],"new":[66,153],"demonstrations":[67],"for":[68],"iterative":[69],"refinement.":[70],"enhance":[72],"diversity":[74],"these":[76],"SEIL":[78,150],"employs":[79],"dual-level":[80],"augmentation:":[81],"(i)":[82],"Model-level,":[83],"using":[84],"an":[85],"Exponential":[86],"Moving":[87],"Average":[88],"(EMA)":[89],"collaborate":[92],"with":[93,137],"primary":[95],"model,":[96],"(ii)":[98],"Environment-level,":[99],"introducing":[100],"slight":[101],"variations":[102],"initial":[104],"object":[105],"positions.":[106],"We":[107],"further":[108],"introduce":[109],"lightweight":[111],"selector":[112],"filters":[114],"complementary":[115],"informative":[117],"generated":[121],"pool":[122],"ensure":[124],"demonstration":[125],"quality.":[126],"These":[127],"curated":[128],"samples":[129],"enable":[130],"achieve":[134],"competitive":[135],"performance":[136,155],"far":[138],"fewer":[139],"examples.":[141],"Extensive":[142],"experiments":[143],"on":[144],"LIBERO":[146],"benchmark":[147],"show":[148],"achieves":[151],"state-of-the-art":[154],"imitation":[158],"learning.":[159],"Code":[160],"is":[161],"available":[162],"at":[163],"<uri":[164],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[165],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/Jasper-aaa/SEIL.git</uri>.":[166]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-04-14T00:00:00"}