{"id":"https://openalex.org/W7123351356","doi":"https://doi.org/10.1109/cdc57313.2025.11312275","title":"A Model-Based Approach to Imitation Learning through Multi-Step Predictions","display_name":"A Model-Based Approach to Imitation Learning through Multi-Step Predictions","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123351356","doi":"https://doi.org/10.1109/cdc57313.2025.11312275"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5122893993","display_name":"Haldun Balim","orcid":null},"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"]},{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haldun Balim","raw_affiliation_strings":["Harvard University,School of Engineering and Applied Sciences,Massachusetts,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University,School of Engineering and Applied Sciences,Massachusetts,USA","institution_ids":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089107349","display_name":"Yang Hu","orcid":"https://orcid.org/0000-0002-7316-508X"},"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"]},{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Hu","raw_affiliation_strings":["Harvard University,School of Engineering and Applied Sciences,Massachusetts,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University,School of Engineering and Applied Sciences,Massachusetts,USA","institution_ids":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409582","display_name":"Yuyang Zhang","orcid":"https://orcid.org/0009-0004-7404-9824"},"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"]},{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuyang Zhang","raw_affiliation_strings":["Harvard University,School of Engineering and Applied Sciences,Massachusetts,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University,School of Engineering and Applied Sciences,Massachusetts,USA","institution_ids":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005814355","display_name":"N. Li","orcid":null},"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"]},{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Na Li","raw_affiliation_strings":["Harvard University,School of Engineering and Applied Sciences,Massachusetts,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University,School of Engineering and Applied Sciences,Massachusetts,USA","institution_ids":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2006","last_page":"2011"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7383000254631042,"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":0.7383000254631042,"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":0.10750000178813934,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.022299999371170998,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6733999848365784},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.5022000074386597},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.423799991607666},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.40149998664855957},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.3903999924659729},{"id":"https://openalex.org/keywords/mean-squared-prediction-error","display_name":"Mean squared prediction error","score":0.36910000443458557},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.33739998936653137},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3206999897956848}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6991000175476074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6985999941825867},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6733999848365784},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6348000168800354},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.5022000074386597},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.423799991607666},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.30169999599456787},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C207673951","wikidata":"https://www.wikidata.org/wiki/Q1303150","display_name":"Compounding","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2687000036239624},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8147134780883789,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1976863523","https://openalex.org/W2166302491","https://openalex.org/W2604382266","https://openalex.org/W2794908222","https://openalex.org/W2806163172","https://openalex.org/W2976205474","https://openalex.org/W4224221644","https://openalex.org/W4246038204","https://openalex.org/W4395047259","https://openalex.org/W7123351356"],"related_works":[],"abstract_inverted_index":{"Imitation":[0],"learning":[1,54],"is":[2],"a":[3,50],"widely":[4],"used":[5],"approach":[6],"for":[7],"training":[8,42],"agents":[9],"to":[10,30,84],"replicate":[11],"expert":[12],"behavior":[13,77],"in":[14,91],"complex":[15],"decision-making":[16],"tasks.":[17],"However,":[18],"existing":[19],"methods":[20],"often":[21],"struggle":[22],"with":[23],"compounding":[24],"errors":[25],"and":[26,37,43,87,94,106],"limited":[27],"generalization,":[28],"due":[29],"the":[31,38,103],"inherent":[32],"challenge":[33],"of":[34,109],"error":[35,107],"correction":[36],"distribution":[39,85],"shift":[40,86],"between":[41],"deployment.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,98],"present":[49],"novel":[51],"model-based":[52],"imitation":[53],"framework":[55],"inspired":[56],"by":[57,65],"model":[58],"predictive":[59,67],"control,":[60],"which":[61],"addresses":[62],"these":[63],"limitations":[64],"integrating":[66],"modeling":[68],"through":[69],"multi-step":[70],"state":[71],"predictions.":[72],"Our":[73],"method":[74],"outperforms":[75],"traditional":[76],"cloning":[78],"numerical":[79],"benchmarks,":[80],"demonstrating":[81],"superior":[82],"robustness":[83],"measurement":[88],"noise":[89],"both":[90],"available":[92],"data":[93],"during":[95],"execution.":[96],"Furthermore,":[97],"provide":[99],"theoretical":[100],"guarantees":[101],"on":[102],"sample":[104],"complexity":[105],"bounds":[108],"our":[110],"method,":[111],"offering":[112],"insights":[113],"into":[114],"its":[115],"convergence":[116],"properties.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-14T00:00:00"}