{"id":"https://openalex.org/W4403851274","doi":"https://doi.org/10.48550/arxiv.2409.16578","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":2024,"publication_date":"2024-09-25","ids":{"openalex":"https://openalex.org/W4403851274","doi":"https://doi.org/10.48550/arxiv.2409.16578"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2409.16578","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.16578","pdf_url":"https://arxiv.org/pdf/2409.16578","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.16578","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089998046","display_name":"Jiaheng Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hu, Jiaheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053943972","display_name":"Rose Hendrix","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hendrix, Rose","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101576595","display_name":"Ali Farhadi","orcid":"https://orcid.org/0000-0001-7249-2380"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farhadi, Ali","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018421415","display_name":"Aniruddha Kembhavi","orcid":"https://orcid.org/0000-0002-7608-7443"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kembhavi, Aniruddha","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060607388","display_name":"Roberto Martin-Martin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin-Martin, Roberto","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001594330","display_name":"Peter Stone","orcid":"https://orcid.org/0000-0002-6795-420X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stone, Peter","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017651065","display_name":"Kuo-Hao Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Kuo-Hao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026693645","display_name":"Kiana Ehsani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ehsani, Kiana","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5089998046"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9958999752998352,"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":0.9958999752998352,"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":0.7630305290222168},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6293678283691406},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5448742508888245},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5078831315040588},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44055551290512085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34360066056251526},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.25888603925704956},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.14613282680511475},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.11532995104789734},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.05922544002532959}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7630305290222168},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6293678283691406},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5448742508888245},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5078831315040588},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44055551290512085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34360066056251526},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25888603925704956},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.14613282680511475},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11532995104789734},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.05922544002532959}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2409.16578","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.16578","pdf_url":"https://arxiv.org/pdf/2409.16578","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"doi:10.48550/arxiv.2409.16578","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.16578","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.16578","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.16578","pdf_url":"https://arxiv.org/pdf/2409.16578","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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":[3,32,45,154,183],"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":[23,48,108,119,127,176],"these":[24,49],"have":[26],"led":[27],"to":[28,55,150,166],"unsatisfactory":[29],"performance,":[30],"where":[31],"policy":[33],"struggles":[34],"with":[35,124,157,171],"unseen":[36,122],"states":[37],"and":[38,51,77,97,102,131,169],"tasks.":[39],"How":[40],"can":[41,147,179],"we":[42,61,162],"break":[43],"performance":[46,92],"plateau":[47],"models":[50],"elevate":[52],"their":[53],"capabilities":[54,152],"new":[56,151,167],"heights?":[57],"this":[59],"paper,":[60],"propose":[62],"FLaRe,":[63],"a":[64,106,174],"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":[94,98,105,133,182],"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":[121,129],"environments,":[123],"absolute":[125],"improvements":[126],"+23.6%":[128],"simulation":[130],"+30.7%":[132],"real":[134],"robots":[135],"over":[136],"prior":[137],"SoTA":[138],"methods.":[139],"By":[140],"utilizing":[141],"only":[142],"sparse":[143],"rewards,":[144],"our":[145],"approach":[146],"enable":[148],"generalizing":[149],"beyond":[153],"pretraining":[155],"data":[156],"minimal":[158],"human":[159],"effort.":[160],"Moreover,":[161],"demonstrate":[163],"rapid":[164],"adaptation":[165],"embodiments":[168],"behaviors":[170],"less":[172],"than":[173],"day":[175],"fine-tuning.":[177],"Videos":[178],"be":[180],"found":[181],"project":[184],"website":[185],"at":[186],"https://robot-flare.github.io/":[187]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}