{"id":"https://openalex.org/W7225818814","doi":"https://doi.org/10.3390/app162211166","title":"Beyond Replay: Automatic Corrections as Direct Policy Supervision for Robotic Manipulation","display_name":"Beyond Replay: Automatic Corrections as Direct Policy Supervision for Robotic Manipulation","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225818814","doi":"https://doi.org/10.3390/app162211166"},"language":"en","primary_location":{"id":"doi:10.3390/app162211166","doi":"https://doi.org/10.3390/app162211166","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app162211166","pdf_url":null,"source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/app162211166","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060139176","display_name":"Xiao Yang","orcid":"https://orcid.org/0000-0002-8933-6461","observed_orcids":["https://orcid.org/0000-0002-8933-6461"]},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Yang","raw_affiliation_strings":["School of Integrated Circuits, University of Chinese Academy of Sciences, Beijing 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, University of Chinese Academy of Sciences, Beijing 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161474230","display_name":"Xiangsheng Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiangsheng Huang","raw_affiliation_strings":["Zidongtaichu Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zidongtaichu Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138235095","display_name":"Haihao Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haihao Lin","raw_affiliation_strings":["School of Integrated Circuits, University of Chinese Academy of Sciences, Beijing 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, University of Chinese Academy of Sciences, Beijing 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161495070","display_name":"Weibang Zhou","orcid":"https://orcid.org/0009-0001-6212-1479","observed_orcids":["https://orcid.org/0009-0001-6212-1479"]},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weibang Zhou","raw_affiliation_strings":["School of Integrated Circuits, University of Chinese Academy of Sciences, Beijing 100049, China"],"raw_orcid":"https://orcid.org/0009-0001-6212-1479","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, University of Chinese Academy of Sciences, Beijing 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138279864","display_name":"Simin Zeng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Simin Zeng","raw_affiliation_strings":["School of Integrated Circuits, University of Chinese Academy of Sciences, Beijing 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, University of Chinese Academy of Sciences, Beijing 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5161474230"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2896},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2896},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"22","first_page":"11166","last_page":"11166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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":0.9984999895095825,"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":0.0013000000035390258,"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":0.0,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6011999845504761},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5698000192642212},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4690999984741211},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45739999413490295},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3682999908924103},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3127000033855438},{"id":"https://openalex.org/C161821725","wikidata":"https://www.wikidata.org/wiki/Q917415","display_name":"Regression testing","level":5,"score":0.29589998722076416},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2937999963760376},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C2779305910","wikidata":"https://www.wikidata.org/wiki/Q5172809","display_name":"Corrective feedback","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C194051981","wikidata":"https://www.wikidata.org/wiki/Q1337691","display_name":"Economic shortage","level":3,"score":0.2565000057220459},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2563999891281128},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/app162211166","doi":"https://doi.org/10.3390/app162211166","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app162211166","pdf_url":null,"source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/app162211166","doi":"https://doi.org/10.3390/app162211166","is_oa":true,"landing_page_url":"https://doi.org/10.3390/app162211166","pdf_url":null,"source":{"id":"https://openalex.org/S4210205812","display_name":"Applied Sciences","issn_l":"2076-3417","issn":["2076-3417"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","norway-1","oarl","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Sciences","raw_type":"journal-article"},"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":[],"abstract_inverted_index":{"Automatic":[0],"corrections":[1,37,156],"offer":[2],"direct":[3,150],"policy":[4],"supervision":[5,138,141],"during":[6],"assisted":[7],"robotic":[8],"reinforcement":[9],"learning.":[10],"We":[11,44],"evaluate":[12],"whether":[13],"regressing":[14],"on":[15,32,48,105,109],"these":[16],"actions":[17],"improves":[18],"learning":[19],"beyond":[20],"their":[21],"use":[22],"in":[23,142],"replay.":[24],"Uniform":[25],"corrective":[26],"distillation":[27],"(UCD)":[28],"adds":[29],"actor":[30,151],"regression":[31,152],"initial":[33],"demonstrations":[34],"and":[35,52,57,60,107,116,134],"online":[36],"to":[38,66],"an":[39],"AutoSERL-derived":[40],"soft":[41],"actor\u2013critic":[42],"system.":[43],"compare":[45],"four":[46],"objectives":[47],"simulated":[49],"spatula":[50,106,121],"hanging":[51],"drawer":[53],"opening":[54],"with":[55,94,118],"fixed":[56],"randomized":[58,63],"starts":[59],"extend":[61],"the":[62,75,82,158],"UCD\u2013baseline":[64],"comparison":[65,129],"five":[67,99,120],"training":[68],"seeds":[69],"per":[70],"method.":[71],"Training":[72],"stops":[73],"when":[74],"shared":[76],"process-success":[77],"criterion":[78],"is":[79,84],"met":[80],"or":[81],"budget":[83],"exhausted;":[85],"each":[86],"returned":[87],"model":[88],"receives":[89],"100":[90],"fresh":[91],"test":[92],"episodes":[93],"task":[95],"assistance":[96],"disabled.":[97],"Across":[98],"seeds,":[100],"UCD":[101,122],"averaged":[102],"100.0%":[103],"success":[104],"91.2%":[108],"drawer,":[110],"versus":[111],"baseline":[112],"means":[113],"of":[114],"71.6%":[115],"79.8%,":[117],"all":[119,143],"models":[123],"achieving":[124],"100/100":[125],"successes.":[126],"A":[127],"separate":[128],"matched":[130],"auxiliary":[131],"batch":[132],"size":[133],"update":[135],"frequency;":[136],"correction-inclusive":[137],"exceeded":[139],"demonstration-only":[140],"six":[144],"task\u2013seed":[145],"pairs.":[146],"These":[147],"results":[148],"support":[149],"for":[153],"reusing":[154],"automatic":[155],"under":[157],"evaluated":[159],"stopping":[160],"protocol.":[161]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}