{"id":"https://openalex.org/W4413925032","doi":"https://doi.org/10.1109/icra55743.2025.11127934","title":"FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning","display_name":"FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925032","doi":"https://doi.org/10.1109/icra55743.2025.11127934"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127934","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/A5089998046","display_name":"Jiaheng Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaheng Hu","raw_affiliation_strings":["Allen Institute for Artificial Intelligence (Ai2)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for Artificial Intelligence (Ai2)","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053943972","display_name":"Rose Hendrix","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rose Hendrix","raw_affiliation_strings":["Allen Institute for Artificial Intelligence (Ai2)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for Artificial Intelligence (Ai2)","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101576595","display_name":"Ali Farhadi","orcid":"https://orcid.org/0000-0001-7249-2380"},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Farhadi","raw_affiliation_strings":["Allen Institute for Artificial Intelligence (Ai2)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for Artificial Intelligence (Ai2)","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018421415","display_name":"Aniruddha Kembhavi","orcid":"https://orcid.org/0000-0002-7608-7443"},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aniruddha Kembhavi","raw_affiliation_strings":["Allen Institute for Artificial Intelligence (Ai2)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for Artificial Intelligence (Ai2)","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065655761","display_name":"Roberto Mart\u00edn-Mart\u00edn","orcid":"https://orcid.org/0000-0002-9586-2759"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roberto Mart\u00edn-Mart\u00edn","raw_affiliation_strings":["University of Texas,Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas,Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001594330","display_name":"Peter Stone","orcid":"https://orcid.org/0000-0002-6795-420X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Stone","raw_affiliation_strings":["University of Texas,Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas,Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017651065","display_name":"Kuo-Hao Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kuo-Hao Zeng","raw_affiliation_strings":["Allen Institute for Artificial Intelligence (Ai2)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for Artificial Intelligence (Ai2)","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026693645","display_name":"Kiana Ehsani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kiana Ehsani","raw_affiliation_strings":["Allen Institute for Artificial Intelligence (Ai2)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for Artificial Intelligence (Ai2)","institution_ids":["https://openalex.org/I4210156221"]}]}],"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":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3617","last_page":"3624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955999851226807,"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":0.9955999851226807,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8583562970161438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6327709555625916},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5778818130493164},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5342969298362732},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.46177589893341064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3825450539588928},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19248288869857788},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09833478927612305}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8583562970161438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6327709555625916},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5778818130493164},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5342969298362732},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.46177589893341064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3825450539588928},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19248288869857788},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09833478927612305},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127934","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":25,"referenced_works":["https://openalex.org/W1483373940","https://openalex.org/W2130726249","https://openalex.org/W2145339207","https://openalex.org/W2788862220","https://openalex.org/W2963411833","https://openalex.org/W2963713397","https://openalex.org/W3035624836","https://openalex.org/W3088310808","https://openalex.org/W3117215073","https://openalex.org/W3141797743","https://openalex.org/W3199020598","https://openalex.org/W3211462570","https://openalex.org/W4383112908","https://openalex.org/W4385430472","https://openalex.org/W4385430679","https://openalex.org/W4385430825","https://openalex.org/W4386075660","https://openalex.org/W4386075839","https://openalex.org/W4386076704","https://openalex.org/W4390874575","https://openalex.org/W4401415287","https://openalex.org/W4402354084","https://openalex.org/W4402776554","https://openalex.org/W4402890475","https://openalex.org/W4409348659"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"In":[0,58],"recent":[1],"years,":[2],"the":[3,32,45,160,192],"Robotics":[4],"field":[5],"has":[6],"initiated":[7],"several":[8],"efforts":[9],"toward":[10],"building":[11],"generalist":[12],"robot":[13],"policies":[14,25,85],"through":[15,44],"large-scale":[16,65,75],"multi-task":[17],"Behavior":[18],"Cloning.":[19],"However,":[20],"direct":[21],"deployments":[22],"of":[23,48,108,119,127,182],"these":[24,49],"have":[26],"led":[27],"to":[28,55,156,172],"unsatisfactory":[29],"performance,":[30],"where":[31],"policy":[33],"struggles":[34],"with":[35,124,163,177],"unseen":[36,122],"states":[37],"and":[38,51,77,97,102,134,175,186],"tasks.":[39],"How":[40],"can":[41,153,188],"we":[42,61,168],"break":[43],"performance":[46,92],"plateau":[47],"models":[50],"elevate":[52],"their":[53],"capabilities":[54,158],"new":[56,157,173],"heights?":[57],"this":[59],"paper,":[60],"propose":[62],"FLaRe,":[63],"a":[64,106,180],"Reinforcement":[66],"Learning":[67],"fine-tuning":[68],"framework":[69],"that":[70],"integrates":[71],"robust":[72],"pre-trained":[73,84],"representations,":[74],"training,":[76],"gradient":[78],"stabilization":[79],"techniques.":[80],"Our":[81],"method":[82],"aligns":[83],"towards":[86],"task":[87],"completion,":[88],"achieving":[89],"state-of-the-art":[90],"(SoTA)":[91],"both":[93],"on":[94,98,105,139,191],"previously":[95],"demonstrated":[96],"entirely":[99],"novel":[100],"tasks":[101],"embodiments.":[103],"Specifically,":[104],"set":[107],"long-horizon":[109],"mobile":[110],"manipulation":[111],"tasks,":[112],"FLaRe":[113],"achieves":[114],"an":[115],"average":[116],"success":[117],"rate":[118],"79.5%":[120],"in":[121,132],"environments,":[123],"absolute":[125],"improvements":[126],"<tex":[128,135],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[129,136],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$+23.6":[130],"\\%$</tex>":[131,138],"simulation":[133],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$+30.7":[137],"real":[140],"robots":[141],"over":[142],"prior":[143],"SoTA":[144],"methods.":[145],"By":[146],"utilizing":[147],"only":[148],"sparse":[149],"rewards,":[150],"our":[151],"approach":[152],"enable":[154],"generalizing":[155],"beyond":[159],"pretraining":[161],"data":[162],"minimal":[164],"human":[165],"effort.":[166],"Moreover,":[167],"demonstrate":[169],"rapid":[170],"adaptation":[171],"embodiments":[174],"behaviors":[176],"less":[178],"than":[179],"day":[181],"fine-tuning.":[183],"Videos,":[184],"code,":[185],"appendix":[187],"be":[189],"found":[190],"project":[193],"website":[194],"at":[195],"robot-flare.github.io":[196]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}