{"id":"https://openalex.org/W4385626984","doi":"https://doi.org/10.1109/tkde.2023.3302804","title":"Sample Efficient Offline-to-Online Reinforcement Learning","display_name":"Sample Efficient Offline-to-Online Reinforcement Learning","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4385626984","doi":"https://doi.org/10.1109/tkde.2023.3302804"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2023.3302804","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2023.3302804","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-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/A5028982929","display_name":"Siyuan Guo","orcid":"https://orcid.org/0000-0002-9304-5405"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210164189","display_name":"Jilin International Studies University","ror":"https://ror.org/05mvcw862","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210164189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Guo","raw_affiliation_strings":["School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Jilin University, Changchun, Jilin, China","International Center of Future Science, Jilin University, Changchun, Jilin, China"],"raw_orcid":"https://orcid.org/0000-0002-9304-5405","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]},{"raw_affiliation_string":"International Center of Future Science, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716","https://openalex.org/I4210164189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089307887","display_name":"Lixin Zou","orcid":"https://orcid.org/0000-0001-6755-871X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lixin Zou","raw_affiliation_strings":["School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0000-0001-6755-871X","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108294333","display_name":"Hechang Chen","orcid":"https://orcid.org/0000-0001-7835-9556"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hechang Chen","raw_affiliation_strings":["School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Jilin University, Changchun, Jilin, China"],"raw_orcid":"https://orcid.org/0000-0001-7835-9556","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078253656","display_name":"Bohao Qu","orcid":"https://orcid.org/0000-0003-3192-8736"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohao Qu","raw_affiliation_strings":["School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Jilin University, Changchun, Jilin, China"],"raw_orcid":"https://orcid.org/0000-0003-3192-8736","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103248929","display_name":"Haotian Chi","orcid":"https://orcid.org/0009-0006-3286-7444"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haotian Chi","raw_affiliation_strings":["School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Jilin University, Changchun, Jilin, China"],"raw_orcid":"https://orcid.org/0009-0006-3286-7444","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036357902","display_name":"Philip S. Yu","orcid":"https://orcid.org/0000-0002-3491-5968"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip S. Yu","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Chicago, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-3491-5968","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029392006","display_name":"Yi Chang","orcid":"https://orcid.org/0000-0003-2697-8093"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210164189","display_name":"Jilin International Studies University","ror":"https://ror.org/05mvcw862","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210164189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Chang","raw_affiliation_strings":["School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Jilin University, Changchun, Jilin, China","International Center of Future Science, Jilin University, Changchun, Jilin, China"],"raw_orcid":"https://orcid.org/0000-0003-2697-8093","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]},{"raw_affiliation_string":"International Center of Future Science, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716","https://openalex.org/I4210164189"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6715,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.94426036,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"36","issue":"3","first_page":"1299","last_page":"1310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9991999864578247,"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/T12288","display_name":"Optimization and Search Problems","score":0.9955000281333923,"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/computer-science","display_name":"Computer science","score":0.7960688471794128},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7106673121452332},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5717743039131165},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.5017905235290527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4882633686065674},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4401959180831909}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7960688471794128},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7106673121452332},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5717743039131165},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.5017905235290527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4882633686065674},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4401959180831909},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2023.3302804","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2023.3302804","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G524871825","display_name":null,"funder_award_id":"61976102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7138386155","display_name":null,"funder_award_id":"U19A2065","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1994616650","https://openalex.org/W2009551863","https://openalex.org/W2158782408","https://openalex.org/W2161966552","https://openalex.org/W2489939061","https://openalex.org/W2963043696","https://openalex.org/W2963341956","https://openalex.org/W3016525976","https://openalex.org/W3038249833","https://openalex.org/W3094502228","https://openalex.org/W3163842339","https://openalex.org/W3173984942","https://openalex.org/W3182414949","https://openalex.org/W4225619808","https://openalex.org/W4281661031","https://openalex.org/W4282813201","https://openalex.org/W4287756699","https://openalex.org/W4287998029","https://openalex.org/W4297838928","https://openalex.org/W4313156423","https://openalex.org/W4360584316","https://openalex.org/W4367319708","https://openalex.org/W4382239271","https://openalex.org/W4402513081","https://openalex.org/W6683603353","https://openalex.org/W6684921986","https://openalex.org/W6730641667","https://openalex.org/W6736057607","https://openalex.org/W6747473740","https://openalex.org/W6748600884","https://openalex.org/W6748839928","https://openalex.org/W6757469721","https://openalex.org/W6763704811","https://openalex.org/W6766978945","https://openalex.org/W6767334564","https://openalex.org/W6770887232","https://openalex.org/W6771838272","https://openalex.org/W6776601253","https://openalex.org/W6779265984","https://openalex.org/W6779656125","https://openalex.org/W6780117753","https://openalex.org/W6780559895","https://openalex.org/W6796589144","https://openalex.org/W6797702751","https://openalex.org/W6798398338","https://openalex.org/W6799359760","https://openalex.org/W6800425027","https://openalex.org/W6802659552","https://openalex.org/W6810745647","https://openalex.org/W6810865680","https://openalex.org/W6810936812","https://openalex.org/W6838356327","https://openalex.org/W6839089550","https://openalex.org/W6872168775"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W2607437843"],"abstract_inverted_index":{"Offline":[0],"reinforcement":[1],"learning":[2,131],"(RL)":[3],"makes":[4],"it":[5,39],"possible":[6],"to":[7,42,68,104,117,164],"train":[8],"the":[9,20,23,45,54,62,105,110,120,138,143,153,166],"agents":[10,28,49,116],"entirely":[11],"from":[12,61],"a":[13,83,123,129],"previously":[14],"collected":[15],"dataset.":[16],"However,":[17],"constrained":[18],"by":[19],"quality":[21],"of":[22,107,112,168],"offline":[24,26,47],"dataset,":[25],"RL":[27,48,58,86],"typically":[29],"have":[30],"limited":[31],"performance":[32],"and":[33,75,91,141,172],"cannot":[34],"be":[35],"directly":[36],"deployed.":[37],"Thus,":[38],"is":[40],"desirable":[41],"further":[43],"finetune":[44],"pretrained":[46],"via":[50,88],"online":[51],"interactions":[52],"with":[53],"environment.":[55],"Existing":[56],"offline-to-online":[57,85,144],"algorithms":[59],"suffer":[60],"low":[63],"sample":[64,154],"efficiency":[65,155],"issue,":[66],"due":[67],"two":[69],"inherent":[70],"challenges,":[71],"i.e.,":[72],"exploration":[73,101,171],"limitation":[74],"distribution":[76,139],"shift.":[77],"To":[78],"this":[79],"end,":[80],"we":[81,96,127,160],"propose":[82,98,128],"sample-efficient":[84],"algorithm":[87],"Optimistic":[89],"Exploration":[90],"Meta":[92],"Adaptation":[93],"(OEMA).":[94],"Specifically,":[95],"first":[97],"an":[99],"optimistic":[100,170],"strategy":[102],"according":[103],"principle":[106],"optimism":[108],"in":[109,122],"face":[111],"uncertainty.":[113],"This":[114],"allows":[115],"sufficiently":[118],"explore":[119],"environment":[121],"stable":[124],"manner.":[125],"Moreover,":[126],"meta":[130,173],"based":[132],"adaptation":[133,145],"method,":[134],"which":[135],"can":[136],"reduce":[137],"shift":[140],"accelerate":[142],"process.":[146],"We":[147],"empirically":[148],"demonstrate":[149],"that":[150],"OEMA":[151],"improves":[152],"on":[156],"D4RL":[157],"benchmark.":[158],"Besides,":[159],"provide":[161],"in-depth":[162],"analyses":[163],"verify":[165],"effectiveness":[167],"both":[169],"adaptation.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}