{"id":"https://openalex.org/W4387185205","doi":"https://doi.org/10.3233/faia230343","title":"OER: Offline Experience Replay for Continual Offline Reinforcement Learning","display_name":"OER: Offline Experience Replay for Continual Offline Reinforcement Learning","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387185205","doi":"https://doi.org/10.3233/faia230343"},"language":"en","primary_location":{"id":"doi:10.3233/faia230343","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230343","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230343","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230343","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088628044","display_name":"Sibo Gai","orcid":"https://orcid.org/0000-0002-9671-7924"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sibo Gai","raw_affiliation_strings":["Fudan University, Shanghai, China","Westlake University, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Westlake University, Zhejiang, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665181","display_name":"Donglin Wang","orcid":"https://orcid.org/0000-0002-8188-3735"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Donglin Wang","raw_affiliation_strings":["Westlake University, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University, Zhejiang, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100317919","display_name":"Li He","orcid":"https://orcid.org/0000-0003-4729-0415"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li He","raw_affiliation_strings":["Westlake University, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University, Zhejiang, China","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100665181"],"corresponding_institution_ids":["https://openalex.org/I3133055985"],"apc_list":null,"apc_paid":null,"fwci":2.9908,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93266533,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":96},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9854999780654907,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9854999780654907,"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/T13553","display_name":"Age of Information Optimization","score":0.9775000214576721,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9466000199317932,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8069376349449158},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7777297496795654},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.7046454548835754},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.6166567802429199},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5045763254165649},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.45818012952804565},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.41252923011779785},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4089944064617157},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.2580889165401459},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.15748360753059387}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8069376349449158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777297496795654},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.7046454548835754},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.6166567802429199},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5045763254165649},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.45818012952804565},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.41252923011779785},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4089944064617157},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.2580889165401459},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.15748360753059387},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230343","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230343","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230343","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230343","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230343","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230343","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387185205.pdf","grobid_xml":"https://content.openalex.org/works/W4387185205.grobid-xml"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1682403713","https://openalex.org/W1757796397","https://openalex.org/W2145339207","https://openalex.org/W2527819024","https://openalex.org/W2554863749","https://openalex.org/W2560647685","https://openalex.org/W2583761661","https://openalex.org/W2770882886","https://openalex.org/W2781726626","https://openalex.org/W2788388592","https://openalex.org/W2788994997","https://openalex.org/W2902456977","https://openalex.org/W2902625698","https://openalex.org/W2904246096","https://openalex.org/W2904453761","https://openalex.org/W2918932727","https://openalex.org/W2947150733","https://openalex.org/W2949268663","https://openalex.org/W2951400270","https://openalex.org/W2963072899","https://openalex.org/W2964048876","https://openalex.org/W2964189064","https://openalex.org/W2978455699","https://openalex.org/W2999710481","https://openalex.org/W3000677656","https://openalex.org/W3009584650","https://openalex.org/W3016525976","https://openalex.org/W3017160304","https://openalex.org/W3025606523","https://openalex.org/W3028766998","https://openalex.org/W3033324992","https://openalex.org/W3034786558","https://openalex.org/W3037440645","https://openalex.org/W3042725540","https://openalex.org/W3048811857","https://openalex.org/W3097784654","https://openalex.org/W3122329924","https://openalex.org/W3123155632","https://openalex.org/W3130177876","https://openalex.org/W3135807039","https://openalex.org/W3138136049","https://openalex.org/W3169813746","https://openalex.org/W3170823761","https://openalex.org/W3172301219","https://openalex.org/W3172360140","https://openalex.org/W3175458185","https://openalex.org/W3179631121","https://openalex.org/W3200307746","https://openalex.org/W3201700917","https://openalex.org/W3205794883","https://openalex.org/W3208475213","https://openalex.org/W3211444363","https://openalex.org/W3211500531","https://openalex.org/W3212041118","https://openalex.org/W3212887262","https://openalex.org/W4221145086","https://openalex.org/W4282813201","https://openalex.org/W4287079698","https://openalex.org/W4287080123","https://openalex.org/W4287177585","https://openalex.org/W4287689437","https://openalex.org/W4287756699","https://openalex.org/W4287814827","https://openalex.org/W4293867591","https://openalex.org/W4295883599","https://openalex.org/W4298053547","https://openalex.org/W4298857966","https://openalex.org/W4301163820","https://openalex.org/W4321649625","https://openalex.org/W4381827212"],"related_works":["https://openalex.org/W4225619808","https://openalex.org/W4388926065","https://openalex.org/W4386160446","https://openalex.org/W4387293922","https://openalex.org/W4226221094","https://openalex.org/W4221145086","https://openalex.org/W4226042081","https://openalex.org/W92125585","https://openalex.org/W4284974072","https://openalex.org/W4376223516"],"abstract_inverted_index":{"The":[0],"capability":[1],"of":[2,10,24,56,77,80,252],"continuously":[3],"learning":[4,21,48,59,87,113,231],"new":[5,43,96,141,168,232,242],"skills":[6],"via":[7],"a":[8,22,42,54,70,140,167,180,241],"sequence":[9,23,55],"pre-collected":[11],"offline":[12,25,46,57,105,212,265],"datasets":[13],"is":[14,183,192],"desired":[15],"for":[16,127,221],"an":[17,51,92,104,163],"agent.":[18],"However,":[19,131],"consecutively":[20],"tasks":[26,60,68],"likely":[27],"leads":[28],"to":[29,121,174,185,194,226,248],"the":[30,78,82,123,128,145,148,151,157,176,187,196,200,204,209,218,228,236,250,256],"catastrophic":[31],"forgetting":[32],"issue":[33],"under":[34],"resource-limited":[35],"scenarios.":[36],"In":[37,259],"this":[38,108],"paper,":[39],"we":[40,110,132,165,234,261],"formulate":[41],"setting,":[44],"continual":[45,112],"reinforcement":[47,58],"(CORL),":[49],"where":[50,179],"agent":[52,93],"learns":[53],"and":[61,98,115,154,203],"pursues":[62],"good":[63],"performance":[64],"on":[65,88,230,255],"all":[66,81,89],"learned":[67,158,184,205,219],"with":[69,240],"small":[71],"replay":[72,119,152,177,201,238,267],"buffer":[73,153,202],"without":[74],"exploring":[75],"any":[76],"environments":[79],"sequential":[83,90],"tasks.":[84],"For":[85],"consistently":[86],"tasks,":[91,233],"requires":[94],"acquiring":[95],"knowledge":[97,102],"meanwhile":[99],"preserving":[100],"old":[101],"in":[103,150,224,279],"manner.":[106],"To":[107,160],"end,":[109],"introduced":[111],"algorithms":[114],"experimentally":[116],"found":[117],"experience":[118,170,237,266],"(ER)":[120],"be":[122],"most":[124,215],"suitable":[125],"algorithm":[126,264],"CORL":[129,138],"problem.":[130],"observe":[133],"that":[134,214,272],"introducing":[135],"ER":[136],"into":[137],"encounters":[139],"distribution":[142,197],"shift":[143],"problem:":[144],"mismatch":[146],"between":[147,199],"experiences":[149],"trajectories":[155],"from":[156,211],"policy.":[159],"address":[161],"such":[162],"issue,":[164],"propose":[166],"model-based":[169],"selection":[171],"(MBES)":[172],"scheme":[173],"build":[175],"buffer,":[178],"transition":[181],"model":[182,191,206,220],"approximate":[186],"state":[188],"distribution.":[189],"This":[190],"used":[193],"bridge":[195],"bias":[198],"by":[207],"filtering":[208],"data":[210,213],"closely":[216],"resembles":[217],"storage.":[222],"Moreover,":[223],"order":[225],"enhance":[227],"ability":[229],"retrofit":[235],"method":[239,275],"dual":[243],"behavior":[244],"cloning":[245],"(DBC)":[246],"architecture":[247],"avoid":[249],"disturbance":[251],"behavior-cloning":[253],"loss":[254],"Q-learning":[257],"process.":[258],"general,":[260],"call":[262],"our":[263,273],"(OER).":[268],"Extensive":[269],"experiments":[270],"demonstrate":[271],"OER":[274],"outperforms":[276],"SOTA":[277],"baselines":[278],"widely-used":[280],"Mujoco":[281],"environments.":[282]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}