{"id":"https://openalex.org/W7204206643","doi":"https://doi.org/10.48550/arxiv.2608.21899","title":"CIDER: Continual Interactive Distillation for Embodied Reinforcement Learning","display_name":"CIDER: Continual Interactive Distillation for Embodied Reinforcement Learning","publication_year":2026,"publication_date":"2026-08-22","ids":{"openalex":"https://openalex.org/W7204206643","doi":"https://doi.org/10.48550/arxiv.2608.21899"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.21899","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21899","pdf_url":"https://arxiv.org/pdf/2608.21899","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,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.21899","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140719796","display_name":"Houlin Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Houlin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125055250","display_name":"Minghui Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Minghui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148166032","display_name":"Guo Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148154022","display_name":"Xuan Du","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Xuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140657370","display_name":"Xiaohan Yan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Xiaohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148090609","display_name":"Chun Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125670762","display_name":"Yuxiang Yan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Yuxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148060917","display_name":"Shukai Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Shukai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126131186","display_name":"Yongcheng Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yongcheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140615105","display_name":"Wei Shan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shan, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5143583893","display_name":"Maoqing Yao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Maoqing","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":0.9907000064849854,"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":0.9907000064849854,"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":0.005499999970197678,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0031999999191612005,"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/continual-reinforcement-learning","display_name":"continual reinforcement learning","score":0.9419999718666077},{"id":"https://openalex.org/keywords/catastrophic-forgetting","display_name":"catastrophic forgetting","score":0.9330000281333923},{"id":"https://openalex.org/keywords/human-in-the-loop-machine-learning","display_name":"human-in-the-loop learning","score":0.7250000238418579},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.7540000081062317},{"id":"https://openalex.org/keywords/teacher-policy","display_name":"teacher policy","score":0.4230000078678131}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8910999894142151},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7742999792098999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7501999735832214},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5968999862670898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5565000176429749},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4941999912261963},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4900999963283539},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.421099990606308},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38429999351501465},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.35749998688697815},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C132758656","wikidata":"https://www.wikidata.org/wiki/Q5307365","display_name":"Dreyfus model of skill acquisition","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.2759999930858612},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.26010000705718994}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.21899","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21899","pdf_url":"https://arxiv.org/pdf/2608.21899","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,"listed_in":[],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.21899","doi":"https://doi.org/10.48550/arxiv.2608.21899","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.21899","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.21899","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21899","pdf_url":"https://arxiv.org/pdf/2608.21899","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,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3153376960","https://openalex.org/W4401416949","https://openalex.org/W4403863399","https://openalex.org/W2962515681","https://openalex.org/W7170084358","https://openalex.org/W7134816757","https://openalex.org/W7092294240","https://openalex.org/W3165631200","https://openalex.org/W4415727183","https://openalex.org/W4383109296"],"abstract_inverted_index":{"Human-in-the-loop":[0],"real-world":[1,46,129,185],"reinforcement":[2,73,187],"learning":[3,48,74,86,93],"enables":[4],"rapid":[5],"acquisition":[6],"of":[7,18],"effective":[8],"robotic":[9],"manipulation":[10,133],"policies":[11],"for":[12,66,107,114],"individual":[13],"tasks,":[14],"often":[15],"within":[16],"tens":[17],"minutes.":[19],"Yet":[20],"it":[21],"remains":[22],"unclear":[23],"how":[24],"to":[25,29,57,102,157],"extend":[26],"this":[27],"paradigm":[28],"continual":[30,47,72,186],"learning,":[31],"where":[32],"a":[33,71,83,123],"single":[34,124],"policy":[35,81],"must":[36],"acquire":[37],"new":[38,88,109,153],"skills":[39],"without":[40],"losing":[41],"previously":[42,142],"learned":[43,143],"behaviors.":[44,117],"Existing":[45],"methods":[49],"do":[50],"not":[51],"explicitly":[52],"constrain":[53],"prior":[54,116],"behaviors,":[55],"leading":[56],"severe":[58],"catastrophic":[59],"forgetting.":[60],"We":[61,97,118],"introduce":[62,99],"Continual":[63],"Interactive":[64,135],"Distillation":[65,136],"Embodied":[67],"Reinforcement":[68],"Learning":[69],"(CIDER),":[70],"framework":[75],"that":[76,176],"freezes":[77],"the":[78,104,172,178],"accumulated":[79],"historical":[80],"as":[82],"teacher":[84],"before":[85],"each":[87,152],"task":[89,92,154],"and":[90,131,182],"interleaves":[91],"with":[94,122],"distillation-based":[95],"retention.":[96],"further":[98],"gradient":[100],"routing":[101],"separate":[103],"gradients":[105],"used":[106,113],"acquiring":[108,151],"tasks":[110,144],"from":[111],"those":[112],"preserving":[115],"evaluate":[119],"our":[120,146],"method":[121],"shared":[125],"actor":[126],"on":[127,141],"six":[128],"household":[130],"industrial":[132],"tasks.":[134],"maintains":[137],"high":[138],"measured":[139],"success":[140],"across":[145],"six-task":[147],"real-robot":[148],"sequence":[149],"while":[150],"in":[155,184],"10":[156],"20":[158],"minutes,":[159],"whereas":[160],"every":[161],"baseline":[162],"forgets":[163],"at":[164],"least":[165],"one":[166],"previous":[167],"task.":[168],"Additional":[169],"ablations":[170],"reveal":[171],"key":[173],"design":[174],"choices":[175],"govern":[177],"tradeoff":[179],"between":[180],"stability":[181],"plasticity":[183],"learning.":[188]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}