{"id":"https://openalex.org/W4416750477","doi":"https://doi.org/10.1109/iros60139.2025.11246167","title":"Offline Imitation Learning upon Arbitrary Demonstrations by Pre-Training Dynamics Representations","display_name":"Offline Imitation Learning upon Arbitrary Demonstrations by Pre-Training Dynamics Representations","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750477","doi":"https://doi.org/10.1109/iros60139.2025.11246167"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-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/A5004124678","display_name":"Haitong Ma","orcid":"https://orcid.org/0000-0002-9943-0638"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haitong Ma","raw_affiliation_strings":["Harvard University,School of Engineering and Applied Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University,School of Engineering and Applied Sciences","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101990493","display_name":"Bo Dai","orcid":"https://orcid.org/0000-0003-0777-9232"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Dai","raw_affiliation_strings":["Georgia Institute of Technology,School of Computational Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Computational Science and Engineering","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050464562","display_name":"Zhaolin Ren","orcid":"https://orcid.org/0009-0006-6502-6430"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaolin Ren","raw_affiliation_strings":["Harvard University,School of Engineering and Applied Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University,School of Engineering and Applied Sciences","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044079782","display_name":"Yebin Wang","orcid":"https://orcid.org/0000-0001-7209-7866"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yebin Wang","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL)","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100368225","display_name":"Na Li","orcid":"https://orcid.org/0000-0003-2626-367X"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Na Li","raw_affiliation_strings":["Harvard University,School of Engineering and Applied Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University,School of Engineering and Applied Sciences","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89698116,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"11639","last_page":"11645"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2669000029563904,"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":0.2669000029563904,"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":0.22789999842643738,"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":0.1915999948978424,"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/leverage","display_name":"Leverage (statistics)","score":0.6809999942779541},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6134999990463257},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.544700026512146},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46480000019073486},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.45899999141693115},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4496999979019165},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41040000319480896},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.4081999957561493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7006000280380249},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6809999942779541},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6134999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5629000067710876},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.544700026512146},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46480000019073486},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4496999979019165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4474000036716461},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41040000319480896},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.4081999957561493},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.3107999861240387},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C186661526","wikidata":"https://www.wikidata.org/wiki/Q13647261","display_name":"Sine","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1999874108","https://openalex.org/W2020282556","https://openalex.org/W2056354534","https://openalex.org/W2158782408","https://openalex.org/W2544683879","https://openalex.org/W2959895084","https://openalex.org/W3039737909","https://openalex.org/W3129637124","https://openalex.org/W4385403811","https://openalex.org/W4391020115","https://openalex.org/W4405786844"],"related_works":[],"abstract_inverted_index":{"Limited":[0],"data":[1,25,78,90,95,150],"has":[2],"become":[3],"a":[4,28,99,133,156],"major":[5],"bottleneck":[6],"in":[7,55,65],"scaling":[8],"up":[9],"offline":[10,52],"imitation":[11],"learning":[12],"(IL).":[13],"In":[14],"this":[15],"paper,":[16],"we":[17,142],"propose":[18],"enhancing":[19],"IL":[20,53],"performance":[21],"under":[22],"limited":[23,94],"expert":[24,127],"by":[26,104],"introducing":[27],"pre-training":[29,115],"stage":[30],"that":[31,46,121,141],"learns":[32],"dynamics":[33,71,111,146],"representations,":[34],"derived":[35],"from":[36,76,148,155],"factorizations":[37],"of":[38,51,87],"the":[39,47,56,61,66,70,81,85,93,110,114],"transition":[40],"dynamics.":[41],"We":[42,97],"first":[43],"theoretically":[44],"justify":[45],"optimal":[48],"decision":[49],"variable":[50],"lies":[54],"representation":[57],"space,":[58],"significantly":[59],"reducing":[60],"parameters":[62],"to":[63,108,151,153],"learn":[64,109,152],"downstream":[67],"IL.":[68],"Moreover,":[69],"representations":[72,112,147],"can":[73,125,143],"be":[74],"learned":[75],"arbitrary":[77],"collected":[79],"with":[80,129],"same":[82],"dynamics,":[83],"allowing":[84],"reuse":[86],"massive":[88],"non-expert":[89],"and":[91],"mitigating":[92],"issues.":[96],"present":[98],"tractable":[100],"loss":[101],"function":[102],"inspired":[103],"noise":[105],"contrastive":[106],"estimation":[107],"at":[113],"stage.":[116],"Experiments":[117,136],"on":[118,137],"MuJoCo":[119],"demonstrate":[120],"our":[122],"proposed":[123],"algorithm":[124],"mimic":[126],"policies":[128],"as":[130,132],"few":[131,157],"single":[134],"trajectory.":[135],"real":[138],"quadrupeds":[139],"show":[140],"leverage":[144],"pre-trained":[145],"simulator":[149],"walk":[154],"real-world":[158],"demonstrations.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}