{"id":"https://openalex.org/W7117453577","doi":"https://doi.org/10.1109/dicta68720.2025.11302428","title":"Evaluating Forgetting in Pretrained Robotic Policy Networks: A Continual Learning Study with Octo","display_name":"Evaluating Forgetting in Pretrained Robotic Policy Networks: A Continual Learning Study with Octo","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7117453577","doi":"https://doi.org/10.1109/dicta68720.2025.11302428"},"language":null,"primary_location":{"id":"doi:10.1109/dicta68720.2025.11302428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta68720.2025.11302428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121469725","display_name":"Yu Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Yu Ding","raw_affiliation_strings":["School of Computing and Information Technology, University of Wollongong,Australia"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Technology, University of Wollongong,Australia","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121118807","display_name":"Lingqiao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lingqiao Liu","raw_affiliation_strings":["School of Computer Science, University of Adelaide,Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Adelaide,Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396041","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0002-5571-3425"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101728024","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0002-0961-0441"},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["School of Computing and Information Technology, University of Wollongong,Australia"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Technology, University of Wollongong,Australia","institution_ids":["https://openalex.org/I204824540"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5121469725"],"corresponding_institution_ids":["https://openalex.org/I204824540"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81357245,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.3928999900817871,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.3928999900817871,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.14300000667572021,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11640000343322754,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/forgetting","display_name":"Forgetting","score":0.8640999794006348},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.39320001006126404},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.36739999055862427},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3264000117778778},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.29109999537467957}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.8640999794006348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5737000107765198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.541100025177002},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.39320001006126404},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35249999165534973},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.29109999537467957},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.2583000063896179},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dicta68720.2025.11302428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta68720.2025.11302428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3433425221","display_name":null,"funder_award_id":"DP220101784","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2996514457","https://openalex.org/W3007769740","https://openalex.org/W3170104202","https://openalex.org/W4205991051","https://openalex.org/W4312238419","https://openalex.org/W4312651322","https://openalex.org/W4385430679","https://openalex.org/W4401414844","https://openalex.org/W4403337227"],"related_works":[],"abstract_inverted_index":{"The":[0,122],"development":[1],"of":[2,55,85,145],"large,":[3],"pretrained":[4,34,64,148],"policy":[5,62,150],"networks":[6,151],"has":[7],"shown":[8],"significant":[9],"promise":[10],"in":[11,88,135,147,160],"robotic":[12,67,149],"manipulation,":[13],"enabling":[14],"models":[15,35],"to":[16,76,82,129],"generalize":[17],"across":[18,114],"diverse":[19,66,119],"tasks":[20,87],"within":[21],"their":[22],"pretraining":[23],"domains.":[24],"However,":[25],"a":[26,69,83,142],"critical":[27],"question":[28],"remains":[29],"largely":[30],"unanswered:":[31],"can":[32],"these":[33],"continually":[36],"acquire":[37],"new":[38,86],"skills":[39],"without":[40],"forgetting":[41,146],"previously":[42],"learned":[43],"ones?":[44],"In":[45],"this":[46,50],"study,":[47],"we":[48],"investigate":[49],"issue":[51],"through":[52],"the":[53,89],"lens":[54],"continual":[56,158],"learning,":[57],"using":[58],"Octo\u2014a":[59],"transformer-based":[60],"diffusion":[61],"model":[63,101],"on":[65],"tasks\u2014as":[68],"representative":[70],"example.":[71],"We":[72],"evaluate":[73],"Octo's":[74],"ability":[75],"retain":[77],"prior":[78],"knowledge":[79],"while":[80],"adapting":[81],"sequence":[84],"RL-Bench":[90],"simulation":[91],"environment.":[92],"Our":[93],"analysis":[94],"compares":[95],"several":[96],"fine-tuning":[97,127],"strategies,":[98],"including":[99],"full":[100],"tuning,":[102,105,113],"action":[103],"head":[104],"transformer":[106],"tuning":[107],"with":[108],"frozen":[109],"heads,":[110],"and":[111,118,152],"prompt":[112],"both":[115],"semantically":[116],"similar":[117],"manipulation":[120],"tasks.":[121],"results":[123],"show":[124],"that":[125],"naive":[126],"leads":[128],"substantial":[130],"catastrophic":[131],"forgetting,":[132],"highlighting":[133],"limitations":[134],"current":[136],"adaptation":[137],"methods.":[138],"This":[139],"work":[140],"provides":[141],"systematic":[143],"evaluation":[144],"offers":[153],"insights":[154],"for":[155],"achieving":[156],"effective":[157],"learning":[159],"robot":[161],"manipulation.":[162]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-29T00:00:00"}