{"id":"https://openalex.org/W4413925003","doi":"https://doi.org/10.1109/icra55743.2025.11128127","title":"FDPP: Fine-Tune Diffusion Policy with Human Preference","display_name":"FDPP: Fine-Tune Diffusion Policy with Human Preference","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925003","doi":"https://doi.org/10.1109/icra55743.2025.11128127"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5070894907","display_name":"Yuxin Chen","orcid":"https://orcid.org/0000-0003-0658-7562"},"institutions":[{"id":"https://openalex.org/I4210099960","display_name":"Systems Control (United States)","ror":"https://ror.org/014tted12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210099960"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxin Chen","raw_affiliation_strings":["UC Berkeley,Mechanical Systems Control Lab,Berkeley,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley,Mechanical Systems Control Lab,Berkeley,CA,USA","institution_ids":["https://openalex.org/I4210099960","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010530960","display_name":"Devesh K. Jha","orcid":"https://orcid.org/0000-0002-7843-9545"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Devesh K. Jha","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064077634","display_name":"Masayoshi Tomizuka","orcid":"https://orcid.org/0000-0003-0206-6639"},"institutions":[{"id":"https://openalex.org/I4210099960","display_name":"Systems Control (United States)","ror":"https://ror.org/014tted12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210099960"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masayoshi Tomizuka","raw_affiliation_strings":["UC Berkeley,Mechanical Systems Control Lab,Berkeley,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley,Mechanical Systems Control Lab,Berkeley,CA,USA","institution_ids":["https://openalex.org/I4210099960","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062272788","display_name":"Diego Romeres","orcid":"https://orcid.org/0000-0002-8603-2438"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diego Romeres","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":27.941,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.99388312,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"12010","last_page":"12016"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11043","display_name":"Merger and Competition Analysis","score":0.07109999656677246,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11043","display_name":"Merger and Competition Analysis","score":0.07109999656677246,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11499","display_name":"ICT Impact and Policies","score":0.06909999996423721,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/diffusion","display_name":"Diffusion","score":0.644555926322937},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5911296010017395},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5172703862190247},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.1963495910167694},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1473178267478943},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.10323736071586609},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.08404430747032166}],"concepts":[{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.644555926322937},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5911296010017395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5172703862190247},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1963495910167694},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1473178267478943},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.10323736071586609},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.08404430747032166}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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":9,"referenced_works":["https://openalex.org/W2119717200","https://openalex.org/W2735318784","https://openalex.org/W2763110165","https://openalex.org/W3039737909","https://openalex.org/W3096831136","https://openalex.org/W3189615635","https://openalex.org/W4383108491","https://openalex.org/W4402354045","https://openalex.org/W4403337227"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Imitation":[0],"learning":[1,67],"from":[2],"human":[3,77],"demonstrations":[4],"enables":[5],"robots":[6],"to":[7,23,26,60],"perform":[8],"complex":[9],"manipulation":[10],"tasks":[11,90],"and":[12,91,115],"has":[13],"recently":[14],"witnessed":[15],"huge":[16],"success.":[17],"However,":[18],"these":[19,36],"techniques":[20],"often":[21],"struggle":[22],"adapt":[24],"behavior":[25,99],"new":[27,76],"preferences":[28,78,92],"or":[29],"changes":[30],"in":[31,70],"the":[32,62,82,118,121],"environment.":[33],"To":[34],"address":[35],"limitations,":[37],"we":[38,104],"propose":[39],"Fine-tuning":[40],"Diffusion":[41],"Policy":[42],"with":[43,65,75],"Human":[44],"Preference":[45],"(FDPP).":[46],"FDPP":[47,95],"learns":[48],"a":[49],"reward":[50,56],"function":[51],"through":[52],"preference-based":[53],"learning.":[54],"This":[55],"is":[57],"then":[58],"used":[59],"fine-tune":[61],"pre-trained":[63,73],"policy":[64,74,98],"reinforcement":[66],"(RL),":[68],"resulting":[69],"alignment":[71],"of":[72,120],"while":[79],"still":[80],"solving":[81],"original":[83],"task.":[84],"Our":[85],"experiments":[86],"across":[87],"various":[88],"robotic":[89],"demonstrate":[93],"that":[94,106],"effectively":[96],"customizes":[97],"without":[100],"compromising":[101],"performance.":[102],"Additionally,":[103],"show":[105],"incorporating":[107],"Kullback-Leibler":[108],"(KL)":[109],"regularization":[110],"during":[111],"fine-tuning":[112],"prevents":[113],"over-fitting":[114],"helps":[116],"maintain":[117],"competencies":[119],"initial":[122],"policy.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
