{"id":"https://openalex.org/W4413393236","doi":"https://doi.org/10.23919/acc63710.2025.11107697","title":"Fast Bandit-based Policy Adaptation in Diverse Environments","display_name":"Fast Bandit-based Policy Adaptation in Diverse Environments","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413393236","doi":"https://doi.org/10.23919/acc63710.2025.11107697"},"language":"en","primary_location":{"id":"doi:10.23919/acc63710.2025.11107697","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","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/A5100352959","display_name":"Ziyi Zhang","orcid":"https://orcid.org/0009-0005-9492-3192"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ziyi Zhang","raw_affiliation_strings":["Carnegie Mellon University,Electrical and Computer Engineering,Pittsburgh,PA,USA,15213"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Electrical and Computer Engineering,Pittsburgh,PA,USA,15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094253784","display_name":"Guannan Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guannan Qu","raw_affiliation_strings":["Carnegie Mellon University,Electrical and Computer Engineering,Pittsburgh,PA,USA,15213"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Electrical and Computer Engineering,Pittsburgh,PA,USA,15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084147009","display_name":"Yorie Nakahira","orcid":"https://orcid.org/0000-0003-3324-4602"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yorie Nakahira","raw_affiliation_strings":["Carnegie Mellon University,Electrical and Computer Engineering,Pittsburgh,PA,USA,15213"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Electrical and Computer Engineering,Pittsburgh,PA,USA,15213","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100352959"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28947768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2458","last_page":"2464"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.9710000157356262,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T13553","display_name":"Age of Information Optimization","score":0.9710000157356262,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9678000211715698,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9085999727249146,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/adaptation","display_name":"Adaptation (eye)","score":0.7367470264434814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.673377513885498},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32232242822647095},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13994324207305908}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7367470264434814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.673377513885498},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32232242822647095},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13994324207305908},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc63710.2025.11107697","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1972870800","https://openalex.org/W2018691083","https://openalex.org/W2039998959","https://openalex.org/W2057012513","https://openalex.org/W2096088498","https://openalex.org/W2108484001","https://openalex.org/W2171423273","https://openalex.org/W2178514702","https://openalex.org/W2300835437","https://openalex.org/W2610645296","https://openalex.org/W4237171445","https://openalex.org/W4393207396"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Autonomous":[0],"systems":[1],"must":[2],"have":[3],"the":[4,57,65,82,86,99,103,107],"ability":[5],"to":[6,9,37],"quickly":[7],"adapt":[8],"various":[10],"situations.":[11],"However,":[12],"adaptation":[13,41],"methods":[14],"often":[15],"require":[16,62],"strong":[17],"assumptions":[18],"about":[19],"system":[20],"structures,":[21],"environmental":[22],"homogeneity,":[23],"and":[24,34,56,121],"multiple":[25],"rollouts.":[26],"In":[27],"this":[28],"work,":[29],"we":[30],"integrate":[31],"multi-armed":[32],"bandit":[33],"model-based":[35],"RL":[36],"design":[38],"a":[39,44,73],"fast":[40],"algorithm":[42,115],"on":[43,98],"single":[45],"trajectory.":[46],"Our":[47],"approach":[48],"achieves":[49],"sublinear":[50],"regret":[51,68],"of":[52,64,88],"$O(\\sqrt":[53],"T":[54],")$,":[55],"performance":[58],"guarantee":[59],"does":[60],"not":[61],"homogeneity":[63],"environment.":[66],"This":[67],"bound":[69],"is":[70,79],"achieved":[71],"using":[72],"novel":[74],"prediction":[75],"error":[76],"metric":[77],"that":[78,113],"minimized":[80],"in":[81,118],"ground-truth":[83],"MDP.":[84],"To":[85],"best":[87],"our":[89,114],"knowledge,":[90],"all":[91],"existing":[92],"results":[93],"with":[94],"provable":[95],"guarantees":[96],"depend":[97],"Bregman":[100],"divergence":[101],"between":[102],"optimal":[104],"policies":[105],"among":[106],"MDPs.":[108],"We":[109],"show":[110],"by":[111],"simulation":[112],"performs":[116],"well":[117],"puzzle":[119],"navigation":[120],"quadcopter":[122],"path-tracking.":[123]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}