{"id":"https://openalex.org/W7168301795","doi":"https://doi.org/10.48550/arxiv.2607.09866","title":"Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement Learning","display_name":"Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement Learning","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7168301795","doi":"https://doi.org/10.48550/arxiv.2607.09866"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.09866","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.09866","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2607.09866","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140636198","display_name":"Wenke Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Wenke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140719376","display_name":"Pei Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Pei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140668655","display_name":"Wenbo Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Wenbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140705573","display_name":"Yizhuo Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yizhuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140593675","display_name":"Jifan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140659994","display_name":"Yixue Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yixue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140628970","display_name":"Yinuo Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yinuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140712057","display_name":"Qingyang Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Qingyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140697410","display_name":"Jianlong Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Jianlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140672804","display_name":"Jian Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140581412","display_name":"Ji-Rong Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen, Ji-Rong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140601062","display_name":"Zhengping Che","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Che, Zhengping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140644471","display_name":"Di Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Di","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":0.6177999973297119,"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":0.6177999973297119,"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":0.12099999934434891,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.03869999945163727,"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":0.847000002861023},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.7110000252723694},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6287999749183655},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.5789999961853027},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.5382000207901001},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.5266000032424927},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.40560001134872437},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.37040001153945923},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.36480000615119934}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.847000002861023},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.7110000252723694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7106000185012817},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6287999749183655},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.5789999961853027},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.5382000207901001},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5266000032424927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4975000023841858},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45159998536109924},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.40560001134872437},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.33219999074935913},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2944999933242798},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2890999913215637},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C191172861","wikidata":"https://www.wikidata.org/wiki/Q7899321","display_name":"Upstream (networking)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.2621999979019165}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.09866","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.09866","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2607.09866","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.09866","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Offline-to-online":[0],"reinforcement":[1,49],"learning":[2],"is":[3,144],"promising":[4],"for":[5,30,116,215],"generalizable":[6,201],"robotic":[7,221],"manipulation,":[8],"yet":[9],"its":[10,34,69,87],"full-stack":[11],"complexity":[12],"obscures":[13],"reproduction":[14],"and":[15,66,75,85,91,104,131,169,198],"diagnosis.":[16],"Within":[17],"such":[18],"systems,":[19],"value":[20,64,83,96,119,148,151,180],"estimation":[21,65],"plays":[22],"a":[23,58,81,105,113],"central":[24,37],"role":[25],"in":[26,47],"prioritizing":[27,174],"heterogeneous":[28,220],"data":[29,213],"policy":[31,45,73,123,217],"improvement.":[32,77],"Despite":[33],"importance,":[35],"the":[36,209],"question":[38],"remains":[39],"underexplored:":[40],"how":[41,118],"value-function":[42],"reliability":[43,88,120],"shapes":[44,121],"optimization":[46],"offline-to-online":[48],"learning.":[50],"To":[51],"answer":[52],"this":[53],"question,":[54],"we":[55],"propose":[56],"Robo-ValueRL,":[57],"unified":[59,114],"framework":[60],"that":[61,141],"enables":[62],"reliable":[63,179],"systematically":[67],"traces":[68],"downstream":[70,122,142],"effects":[71],"on":[72,109,193,200],"pretraining":[74,103,184],"online":[76,110,134,171,186],"Concretely,":[78],"Robo-ValueRL":[79],"learns":[80],"history-conditioned":[82],"estimator":[84],"evaluates":[86],"through":[89,182],"global-progress":[90],"local-preference":[92],"metrics.":[93],"These":[94],"resulting":[95],"estimates":[97],"are":[98],"propagated":[99],"into":[100],"quality-conditioned":[101],"consistency-policy":[102],"residual":[106],"adaptation":[107],"module":[108],"rollouts,":[111],"providing":[112],"testbed":[115],"analyzing":[117],"performance.":[124],"Across":[125],"240":[126],"hours":[127],"of":[128,211],"offline":[129,159,183],"demonstrations":[130],"over":[132],"3,000":[133],"rollout":[135,176],"trajectories,":[136],"our":[137,188],"extensive":[138],"experiments":[139],"show":[140],"performance":[143],"strongly":[145],"associated":[146],"with":[147,185],"reliability.":[149],"Reliable":[150],"functions":[152],"provide":[153],"better":[154],"action-quality":[155],"estimates,":[156],"allowing":[157],"value-guided":[158,212],"RL":[160],"to":[161],"scale":[162],"more":[163],"effectively":[164],"than":[165],"quality-agnostic":[166],"behavior":[167],"cloning,":[168],"stabilize":[170],"improvement":[172,218],"by":[173],"high-quality":[175],"data.":[177],"Integrating":[178],"guidance":[181],"improvement,":[187],"system":[189],"achieves":[190],"86%":[191],"success":[192],"millimeter-level":[194],"precise":[195],"chip":[196],"insertion":[197],"84%":[199],"block":[202],"disassembly.":[203],"We":[204],"hope":[205],"these":[206],"findings":[207],"highlight":[208],"importance":[210],"utilization":[214],"effective":[216],"from":[219],"experience.":[222]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-15T00:00:00"}