{"id":"https://openalex.org/W7166150739","doi":"https://doi.org/10.48550/arxiv.2606.27353","title":"Continual Robot Policy Learning via Variational Neural Dynamics","display_name":"Continual Robot Policy Learning via Variational Neural Dynamics","publication_year":2026,"publication_date":"2026-06-25","ids":{"openalex":"https://openalex.org/W7166150739","doi":"https://doi.org/10.48550/arxiv.2606.27353"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.27353","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27353","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.2606.27353","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031291897","display_name":"Jiaxu Xing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing, Jiaxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139434243","display_name":"Zhiyuan Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Zhiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081404350","display_name":"Yunfan Ren","orcid":"https://orcid.org/0000-0002-5392-8924"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Yunfan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092418578","display_name":"Ismail Geles","orcid":"https://orcid.org/0009-0006-2940-0675"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geles, Ismail","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076132844","display_name":"Yifan Zhai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhai, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017656696","display_name":"Rudolf Reiter","orcid":"https://orcid.org/0009-0007-7635-2132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reiter, Rudolf","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139447614","display_name":"Davide Scaramuzza","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Scaramuzza, Davide","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":0.5162000060081482,"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":0.5162000060081482,"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":0.13230000436306,"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":0.05490000173449516,"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/trajectory","display_name":"Trajectory","score":0.660099983215332},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6309999823570251},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6014000177383423},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5550000071525574},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4846999943256378},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.478300005197525},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4092000126838684},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.3785000145435333},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.3783000111579895},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.37540000677108765}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.660099983215332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6394000053405762},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6309999823570251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6169999837875366},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6014000177383423},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5550000071525574},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4846999943256378},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4092000126838684},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36000001430511475},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3375000059604645},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2506999969482422},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.27353","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27353","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.2606.27353","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27353","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":[{"display_name":"Affordable and clean energy","score":0.6225258111953735,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Robots":[0],"deployed":[1,33],"in":[2,197],"the":[3,41,102,114,118,133,152,174,191,220],"real":[4,82,149,184],"world":[5],"rarely":[6],"operate":[7],"under":[8,69,179,188],"a":[9,57,77,92],"single":[10],"fixed":[11],"dynamics":[12,79,130,157],"model:":[13],"wind":[14],"changes,":[15],"payloads":[16],"vary,":[17],"batteries":[18],"drain,":[19],"contacts":[20],"shift,":[21],"and":[22,32,71,109,117,168,212,217],"hardware":[23],"wears.":[24],"Yet":[25],"most":[26],"learning-based":[27],"controllers":[28],"are":[29,141],"trained":[30],"once":[31],"as":[34],"if":[35],"learning":[36,59,121],"were":[37],"complete.":[38],"This":[39],"prevents":[40],"robot":[42,67],"from":[43,81,106,132,147,194],"using":[44,127],"deployment":[45],"experience":[46,64],"to":[47,65,154],"further":[48],"improve":[49,66],"task":[50],"performance.":[51],"In":[52],"this":[53,110],"work,":[54],"we":[55,171],"propose":[56],"continual":[58],"framework":[60,175],"that":[61,173],"uses":[62],"real-world":[63,169],"policies":[68],"hidden":[70,104],"recurring":[72,156,195],"dynamics.":[73],"Our":[74],"method":[75],"learns":[76],"condition-aware":[78],"model":[80,116],"state-action":[83],"trajectories":[84],"by":[85,143,158,215],"combining":[86],"an":[87],"analytical":[88],"physics":[89],"prior":[90],"with":[91],"neural":[93],"residual":[94,115,162,205],"for":[95],"unmodeled":[96],"effects.":[97],"A":[98],"recurrent":[99],"encoder":[100],"infers":[101],"current":[103],"condition":[105],"recent":[107,148],"interaction,":[108,150],"estimate":[111],"conditions":[112,140,144],"both":[113],"policy.":[119],"Policy":[120],"is":[122],"performed":[123],"via":[124],"differentiable":[125],"simulation":[126,166],"diverse":[128,180],"learned":[129],"sampled":[131,139],"latent":[134],"model.":[135],"At":[136],"deployment,":[137],"these":[138],"replaced":[142],"inferred":[145],"online":[146,204,222],"allowing":[151],"policy":[153,177,192],"recover":[155],"recognition":[159],"rather":[160],"than":[161,203],"re-fitting.":[163,206],"Through":[164],"extensive":[165],"studies":[167],"experiments,":[170],"demonstrate":[172],"improves":[176],"performance":[178],"unobserved":[181],"disturbances.":[182],"On":[183],"quadrotor":[185],"trajectory":[186],"tracking":[187,213],"changing":[189],"wind,":[190],"recovers":[193],"disturbances":[196],"roughly":[198],"1s,":[199],"about":[200],"5x":[201],"faster":[202],"It":[207],"also":[208],"reduces":[209],"large-disturbance":[210],"hover":[211],"errors":[214],"65.7%":[216],"53.3%":[218],"over":[219],"state-of-the-art":[221],"adaptation":[223],"approaches":[224]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-27T00:00:00"}