{"id":"https://openalex.org/W7160117849","doi":"https://doi.org/10.48550/arxiv.2605.00416","title":"Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies","display_name":"Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7160117849","doi":"https://doi.org/10.48550/arxiv.2605.00416"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.00416","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00416","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.00416","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135185064","display_name":"Yi Wang","orcid":"https://orcid.org/0000-0002-2067-5465"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101788002","display_name":"Xinchen Li","orcid":"https://orcid.org/0000-0002-7412-7157"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xinchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135241560","display_name":"Pengwei Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Pengwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125502989","display_name":"Pu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Pu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047621887","display_name":"Buqing Nie","orcid":"https://orcid.org/0000-0001-7419-2672"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nie, Buqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125700942","display_name":"Yunuo Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Yunuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135163993","display_name":"Qinglin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qinglin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041653678","display_name":"Chendi Qu","orcid":"https://orcid.org/0009-0006-8791-085X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qu, Chendi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135265289","display_name":"Jeffrey Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jeffrey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135225230","display_name":"Jianheng Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Jianheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135164577","display_name":"Xinlin Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Xinlin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126737441","display_name":"Jingshun Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jingshun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079639639","display_name":"Mingjie Pan","orcid":"https://orcid.org/0000-0002-4602-1523"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Mingjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135127376","display_name":"Siyuan Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Siyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135199225","display_name":"Zhi Chen","orcid":"https://orcid.org/0000-0002-7871-1860"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135152958","display_name":"Jianlan Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Jianlan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.7893999814987183,"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":0.7893999814987183,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.05249999836087227,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.04830000177025795,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7817999720573425},{"id":"https://openalex.org/keywords/generalist-and-specialist-species","display_name":"Generalist and specialist species","score":0.7310000061988831},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6158999800682068},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5504999756813049},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5030999779701233},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.501800000667572},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3709999918937683}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7817999720573425},{"id":"https://openalex.org/C45371612","wikidata":"https://www.wikidata.org/wiki/Q3058587","display_name":"Generalist and specialist species","level":3,"score":0.7310000061988831},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6158999800682068},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5889999866485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5631999969482422},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5504999756813049},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5030999779701233},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.501800000667572},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4212000072002411},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3709999918937683},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3093000054359436},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2892000079154968},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2778835581","wikidata":"https://www.wikidata.org/wiki/Q2916098","display_name":"Autonomous robot","level":4,"score":0.2565000057220459},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.00416","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00416","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.00416","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00416","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generalist":[0],"robot":[1,87],"policies":[2],"increasingly":[3],"benefit":[4],"from":[5,59,92],"large-scale":[6],"pretraining,":[7],"but":[8],"offline":[9],"data":[10],"alone":[11],"is":[12],"insufficient":[13],"for":[14,50,104,114],"robust":[15,105],"real-world":[16,134],"deployment.":[17],"Deployed":[18],"robots":[19,131],"encounter":[20],"distribution":[21],"shifts,":[22],"long-tail":[23],"failures,":[24],"task":[25],"variations,":[26],"and":[27,75,81,141],"human":[28,82],"correction":[29],"opportunities":[30],"that":[31],"fixed":[32],"demonstration":[33],"datasets":[34],"cannot":[35],"fully":[36],"capture.":[37],"We":[38,122],"present":[39],"Learning":[40,102],"While":[41],"Deploying":[42],"(LWD),":[43],"a":[44,60,86,126],"fleet-scale":[45],"offline-to-online":[46],"reinforcement":[47],"learning":[48,91],"framework":[49],"continual":[51],"post-training":[52],"of":[53,128,160],"generalist":[54,148],"Vision-Language-Action":[55],"(VLA)":[56],"policies.":[57],"Starting":[58],"pretrained":[61],"VLA":[62,119],"policy,":[63],"LWD":[64,97,124],"closes":[65],"the":[66,163],"loop":[67],"between":[68],"deployment,":[69],"shared":[70],"physical":[71],"experience,":[72],"policy":[73,115,149],"improvement,":[74],"redeployment":[76],"by":[77],"using":[78],"autonomous":[79],"rollouts":[80],"interventions":[83],"collected":[84],"across":[85,132],"fleet.":[88],"To":[89],"stabilize":[90],"heterogeneous,":[93],"sparse-reward":[94],"fleet":[95,127,152],"data,":[96],"combines":[98],"Distributional":[99],"Implicit":[100],"Value":[101],"(DIVL)":[103],"value":[106],"estimation":[107],"with":[108,162],"Q-learning":[109],"via":[110],"Adjoint":[111],"Matching":[112],"(QAM)":[113],"extraction":[116],"in":[117],"flow-based":[118],"action":[120],"generators.":[121],"validate":[123],"on":[125,166],"16":[129],"dual-arm":[130],"eight":[133],"manipulation":[135],"tasks,":[136],"including":[137],"semantic":[138],"grocery":[139],"restocking":[140],"3--5":[142],"minute":[143],"long-horizon":[144,167],"tasks.":[145,168],"A":[146],"single":[147],"improves":[150],"as":[151],"experience":[153],"accumulates,":[154],"reaching":[155],"an":[156],"average":[157],"success":[158],"rate":[159],"95%,":[161],"largest":[164],"gains":[165]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-05T00:00:00"}