{"id":"https://openalex.org/W4401415430","doi":"https://doi.org/10.1109/icra57147.2024.10610701","title":"Weighting Online Decision Transformer with Episodic Memory for Offline-to-Online Reinforcement Learning","display_name":"Weighting Online Decision Transformer with Episodic Memory for Offline-to-Online Reinforcement Learning","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401415430","doi":"https://doi.org/10.1109/icra57147.2024.10610701"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5110127141","display_name":"Xiao Ma","orcid":"https://orcid.org/0009-0002-7260-9504"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Ma","raw_affiliation_strings":["Nanjing University,National Key Laboratory for Novel Software Technology,Department of Computer Science and Technology,Nanjing,PRC,210023"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,National Key Laboratory for Novel Software Technology,Department of Computer Science and Technology,Nanjing,PRC,210023","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101402002","display_name":"Wu-Jun Li","orcid":"https://orcid.org/0000-0003-2499-4006"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu-Jun Li","raw_affiliation_strings":["Nanjing University,National Key Laboratory for Novel Software Technology,Department of Computer Science and Technology,Nanjing,PRC,210023"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,National Key Laboratory for Novel Software Technology,Department of Computer Science and Technology,Nanjing,PRC,210023","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10793","last_page":"10799"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10603","display_name":"Smart Grid Energy Management","score":0.9803000092506409,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8096269369125366},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.757746696472168},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.567227840423584},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5581971406936646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5126763582229614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5039941668510437},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.47243794798851013},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15676456689834595},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11377865076065063}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8096269369125366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.757746696472168},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.567227840423584},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5581971406936646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5126763582229614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5039941668510437},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.47243794798851013},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15676456689834595},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11377865076065063},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.550000011920929}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W644076287","https://openalex.org/W2076337359","https://openalex.org/W2165031188","https://openalex.org/W2436711315","https://openalex.org/W2547875792","https://openalex.org/W2896457183","https://openalex.org/W2964082094","https://openalex.org/W3016525976","https://openalex.org/W3022566517","https://openalex.org/W3033324992","https://openalex.org/W3094502228","https://openalex.org/W3134294674","https://openalex.org/W3169291081","https://openalex.org/W3189480080","https://openalex.org/W3191807689","https://openalex.org/W3205794883","https://openalex.org/W3206246732","https://openalex.org/W3211360571","https://openalex.org/W4205431832","https://openalex.org/W4226151089","https://openalex.org/W4226435594","https://openalex.org/W4283205689","https://openalex.org/W4287126489","https://openalex.org/W4287998029","https://openalex.org/W4292779060","https://openalex.org/W4294811378","https://openalex.org/W4295356277","https://openalex.org/W4297732320","https://openalex.org/W4297812239","https://openalex.org/W4307225071","https://openalex.org/W4307323396","https://openalex.org/W4315588599","https://openalex.org/W4378715832","https://openalex.org/W4385245566","https://openalex.org/W4386897417","https://openalex.org/W4389315147","https://openalex.org/W6718359804","https://openalex.org/W6729448088","https://openalex.org/W6734330393","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6770887232","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6778883912","https://openalex.org/W6779265984","https://openalex.org/W6784333009","https://openalex.org/W6791277150","https://openalex.org/W6796289742","https://openalex.org/W6802659552","https://openalex.org/W6802704075","https://openalex.org/W6803709789","https://openalex.org/W6804244202","https://openalex.org/W6804404469","https://openalex.org/W6810745647","https://openalex.org/W6811554491","https://openalex.org/W6838940190","https://openalex.org/W6842456838","https://openalex.org/W6843759960","https://openalex.org/W6846741855","https://openalex.org/W6849153783","https://openalex.org/W6853057106"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2108418243","https://openalex.org/W2127804977","https://openalex.org/W164103134","https://openalex.org/W2787352659","https://openalex.org/W1970611213","https://openalex.org/W4206560911","https://openalex.org/W4372260270"],"abstract_inverted_index":{"Offline":[0,23],"reinforcement":[1],"learning":[2],"(RL)":[3],"has":[4],"been":[5],"shown":[6],"to":[7,92,117,124,155],"be":[8],"successfully":[9],"modeled":[10],"as":[11],"a":[12,39,103,144,149],"sequence":[13,52,133],"modeling":[14],"problem,":[15],"drawing":[16],"inspiration":[17],"from":[18,63,94],"the":[19,29,32,64,69,79,86,95,132,139],"success":[20],"of":[21,31],"Transformers.":[22],"RL":[24,37,55,135],"is":[25,38,47],"often":[26],"limited":[27],"by":[28],"quality":[30],"offline":[33],"dataset,":[34],"so":[35],"offline-to-online":[36,54],"more":[40],"realistic":[41],"setting.":[42],"Online":[43],"decision":[44,111],"transformer":[45,112],"(ODT)":[46],"an":[48,126],"effective":[49,106],"and":[50],"representative":[51],"modeling-based":[53,134],"method.":[56],"Despite":[57],"its":[58],"effectiveness,":[59],"ODT":[60],"still":[61],"suffers":[62],"sample":[65,74,119,157,169],"inefficiency":[66,75],"problem":[67,76],"during":[68],"online":[70,110],"fine-tuning":[71],"phase.":[72],"This":[73],"arises":[77],"because":[78],"agent":[80],"treats":[81],"all":[82],"state-action":[83],"pairs":[84],"in":[85],"replay":[87,96],"buffer":[88],"equally":[89],"when":[90],"trying":[91],"learn":[93],"buffer.":[97],"In":[98],"this":[99],"paper,":[100],"we":[101,142],"propose":[102,143],"simple":[104],"yet":[105],"method,":[107],"called":[108],"weighting":[109,150],"with":[113,148],"episodic":[114,127],"memory":[115,128],"(WODTEM),":[116],"improve":[118,156,168],"efficiency.":[120,158,170],"We":[121],"first":[122],"attempt":[123],"introduce":[125],"(EM)":[129],"mechanism":[130],"into":[131],"methods.":[136],"By":[137],"utilizing":[138],"EM":[140],"mechanism,":[141],"novel":[145],"training":[146],"objective":[147],"function,":[151],"based":[152],"on":[153,161],"ODT,":[154],"Experimental":[159],"results":[160],"multiple":[162],"tasks":[163],"show":[164],"that":[165],"WODTEM":[166],"can":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}