{"id":"https://openalex.org/W4396506409","doi":"https://doi.org/10.1109/tnnls.2024.3385570","title":"Policy Correction and State-Conditioned Action Evaluation for Few-Shot Lifelong Deep Reinforcement Learning","display_name":"Policy Correction and State-Conditioned Action Evaluation for Few-Shot Lifelong Deep Reinforcement Learning","publication_year":2024,"publication_date":"2024-04-30","ids":{"openalex":"https://openalex.org/W4396506409","doi":"https://doi.org/10.1109/tnnls.2024.3385570","pmid":"https://pubmed.ncbi.nlm.nih.gov/38687668"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3385570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3385570","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100771701","display_name":"Meng Xu","orcid":"https://orcid.org/0000-0003-4857-5439"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Meng Xu","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-4857-5439","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071933192","display_name":"Xinhong Chen","orcid":"https://orcid.org/0000-0002-8563-148X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xinhong Chen","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-8563-148X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100356291","display_name":"Jianping Wang","orcid":"https://orcid.org/0000-0002-9318-1482"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jianping Wang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-9318-1482","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":2.4012,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.89588431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"36","issue":"4","first_page":"6843","last_page":"6857"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5997999906539917,"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":0.5997999906539917,"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":0.7408135533332825},{"id":"https://openalex.org/keywords/lifelong-learning","display_name":"Lifelong learning","score":0.6985298991203308},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6678059697151184},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6254702806472778},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5953048467636108},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4270954430103302},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42441269755363464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4109012484550476},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4015459418296814},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.38892513513565063},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.38191428780555725},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.17608016729354858},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.1271875500679016},{"id":"https://openalex.org/keywords/pedagogy","display_name":"Pedagogy","score":0.11967724561691284},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.11317449808120728},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1029183566570282},{"id":"https://openalex.org/keywords/management","display_name":"Management","score":0.1008075475692749},{"id":"https://openalex.org/keywords/metallurgy","display_name":"Metallurgy","score":0.07061058282852173},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0602477490901947}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7408135533332825},{"id":"https://openalex.org/C108771440","wikidata":"https://www.wikidata.org/wiki/Q368475","display_name":"Lifelong learning","level":2,"score":0.6985298991203308},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6678059697151184},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6254702806472778},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5953048467636108},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4270954430103302},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42441269755363464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4109012484550476},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4015459418296814},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.38892513513565063},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.38191428780555725},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.17608016729354858},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1271875500679016},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.11967724561691284},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.11317449808120728},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1029183566570282},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.1008075475692749},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.07061058282852173},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0602477490901947},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3385570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3385570","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:38687668","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38687668","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3533657152","display_name":null,"funder_award_id":"11218621","funder_id":"https://openalex.org/F4320322887","funder_display_name":"The Research Council"},{"id":"https://openalex.org/G3802291057","display_name":null,"funder_award_id":"R5060-19","funder_id":"https://openalex.org/F4320307285","funder_display_name":"Impact Fund"}],"funders":[{"id":"https://openalex.org/F4320307285","display_name":"Impact Fund","ror":"https://ror.org/00jb20j87"},{"id":"https://openalex.org/F4320322887","display_name":"The Research Council","ror":"https://ror.org/03tcppy59"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W2473930607","https://openalex.org/W2560647685","https://openalex.org/W2798644314","https://openalex.org/W2920933065","https://openalex.org/W2964048876","https://openalex.org/W2978098801","https://openalex.org/W2982006683","https://openalex.org/W3014664339","https://openalex.org/W3046093665","https://openalex.org/W3046814132","https://openalex.org/W3048941751","https://openalex.org/W3091958244","https://openalex.org/W3157870065","https://openalex.org/W3202264206","https://openalex.org/W4280508537","https://openalex.org/W4283365039","https://openalex.org/W4286751599","https://openalex.org/W4308177782","https://openalex.org/W4315784722","https://openalex.org/W4379385867","https://openalex.org/W4379620511","https://openalex.org/W4382318178","https://openalex.org/W4386607612","https://openalex.org/W4390399690","https://openalex.org/W6716109767","https://openalex.org/W6738613105","https://openalex.org/W6743495212","https://openalex.org/W6749399654","https://openalex.org/W6753337839","https://openalex.org/W6756754374","https://openalex.org/W6760539816","https://openalex.org/W6762358693","https://openalex.org/W6771838272","https://openalex.org/W6786083373","https://openalex.org/W6791509694","https://openalex.org/W6791547009","https://openalex.org/W6795826604","https://openalex.org/W6796160345","https://openalex.org/W6796764164","https://openalex.org/W6802227391","https://openalex.org/W6802999184","https://openalex.org/W6810488170","https://openalex.org/W6810594387","https://openalex.org/W6839015648","https://openalex.org/W6839272463","https://openalex.org/W6839330762","https://openalex.org/W6839621807","https://openalex.org/W6843543632","https://openalex.org/W6844961931","https://openalex.org/W6846406187","https://openalex.org/W6850705331","https://openalex.org/W6858732062"],"related_works":["https://openalex.org/W2364105709","https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2384383462","https://openalex.org/W2380954666","https://openalex.org/W2773965352","https://openalex.org/W422428167","https://openalex.org/W1981922029","https://openalex.org/W2037025106","https://openalex.org/W2499777278"],"abstract_inverted_index":{"Lifelong":[0],"deep":[1],"reinforcement":[2],"learning":[3],"(DRL)":[4],"approaches":[5],"are":[6],"commonly":[7],"employed":[8],"to":[9,12,48,113,118,127,161],"adapt":[10],"continuously":[11],"new":[13,50,104],"tasks":[14],"without":[15],"forgetting":[16],"previously":[17,56],"acquired":[18,31],"knowledge.":[19],"While":[20],"current":[21],"lifelong":[22,78,168,201],"DRL":[23,79,169,176,202],"methods":[24,80,170,177,203],"have":[25,154],"shown":[26],"promising":[27],"advancements":[28],"in":[29,138,148],"retaining":[30],"knowledge,":[32],"they":[33],"suffer":[34],"from":[35,55],"significant":[36],"adaptation":[37,101,150],"efforts":[38],"(i.e.,":[39],"longer":[40],"training":[41,102,180],"duration)":[42],"and":[43,134,144,171,184],"suboptimal":[44],"policy":[45,143],"when":[46],"transferring":[47],"a":[49,59,72,107],"task":[51],"that":[52,75,193],"significantly":[53],"deviates":[54],"learned":[57],"tasks,":[58],"phenomenon":[60],"known":[61],"as":[62],"the":[63,82,95,114,120,136,142,197],"few-shot":[64,85,175],"generalization":[65],"challenge.":[66],"In":[67],"this":[68],"work,":[69],"we":[70,88,132],"propose":[71],"generic":[73],"approach":[74,164],"equips":[76],"existing":[77],"with":[81,165],"capability":[83],"of":[84,97,122,187,199],"generalization.":[86],"First,":[87],"employ":[89],"selective":[90],"experience":[91,96],"reuse":[92],"by":[93,204],"leveraging":[94],"encountered":[98],"states,":[99],"improving":[100],"for":[103],"tasks.":[105],"Then,":[106],"relaxed":[108],"softmax":[109],"function":[110],"is":[111],"applied":[112],"target":[115],"Q":[116,124],"values":[117],"improve":[119],"accuracy":[121],"evaluated":[123],"values,":[125],"leading":[126],"more":[128],"optimal":[129],"policies.":[130],"Finally,":[131],"measure":[133],"reduce":[135],"discrepancy":[137],"data":[139],"distribution":[140],"between":[141],"off-policy":[145],"samples,":[146],"resulting":[147],"improved":[149],"efficiency.":[151],"Extensive":[152],"experiments":[153],"been":[155],"conducted":[156],"on":[157],"three":[158],"typical":[159],"benchmarks":[160],"compare":[162],"our":[163,194],"six":[166,200],"representative":[167],"two":[172],"state-of-the-art":[173],"(SOTA)":[174],"regarding":[178],"their":[179],"speed,":[181],"episode":[182],"return,":[183],"average":[185],"return":[186,198],"all":[188],"episodes.":[189],"Experimental":[190],"results":[191],"substantiate":[192],"method":[195],"improves":[196],"at":[205],"least":[206],"25%.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}