{"id":"https://openalex.org/W4379620511","doi":"https://doi.org/10.1109/tnnls.2023.3280085","title":"Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization","display_name":"Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization","publication_year":2023,"publication_date":"2023-06-07","ids":{"openalex":"https://openalex.org/W4379620511","doi":"https://doi.org/10.1109/tnnls.2023.3280085","pmid":"https://pubmed.ncbi.nlm.nih.gov/37285252"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3280085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3280085","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/A5073311567","display_name":"Tiantian Zhang","orcid":"https://orcid.org/0000-0002-0204-4758"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiantian Zhang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China","Tencent AI Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0204-4758","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070351115","display_name":"Zichuan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zichuan Lin","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100615777","display_name":"Yuxing Wang","orcid":"https://orcid.org/0000-0001-8516-6111"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxing Wang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073681676","display_name":"Deheng Ye","orcid":"https://orcid.org/0000-0002-1754-1837"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deheng Ye","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-1754-1837","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065153972","display_name":"Qiang Fu","orcid":"https://orcid.org/0000-0003-4100-2777"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Fu","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092105270","display_name":"Wei Yang","orcid":"https://orcid.org/0000-0003-2140-0313"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Yang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100737125","display_name":"Xueqian Wang","orcid":"https://orcid.org/0000-0003-3542-0593"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqian Wang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3542-0593","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100644629","display_name":"Bin Liang","orcid":"https://orcid.org/0000-0002-7163-345X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7163-345X","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032061647","display_name":"Bo Yuan","orcid":"https://orcid.org/0000-0003-2169-0007"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Yuan","raw_affiliation_strings":["Research Institute of Tsinghua University in Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2169-0007","affiliations":[{"raw_affiliation_string":"Research Institute of Tsinghua University in Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100754504","display_name":"Xiu Li","orcid":"https://orcid.org/0000-0003-0403-1923"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiu Li","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0403-1923","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6301,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86672067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"35","issue":"10","first_page":"14588","last_page":"14602"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.992900013923645,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9900000095367432,"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/contextualization","display_name":"Contextualization","score":0.8981784582138062},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8151905536651611},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.577930212020874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5728016495704651},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.549286961555481},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47568047046661377},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18667209148406982},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.05624765157699585}],"concepts":[{"id":"https://openalex.org/C2780712339","wikidata":"https://www.wikidata.org/wiki/Q5165204","display_name":"Contextualization","level":3,"score":0.8981784582138062},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8151905536651611},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.577930212020874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5728016495704651},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.549286961555481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47568047046661377},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18667209148406982},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05624765157699585},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3280085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3280085","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:37285252","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37285252","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1551893515","https://openalex.org/W1682403713","https://openalex.org/W1994955764","https://openalex.org/W2060277733","https://openalex.org/W2115524942","https://openalex.org/W2119717200","https://openalex.org/W2560647685","https://openalex.org/W2736601468","https://openalex.org/W2902332709","https://openalex.org/W2904861519","https://openalex.org/W2943927637","https://openalex.org/W2962707369","https://openalex.org/W2963072899","https://openalex.org/W2964048876","https://openalex.org/W2964189064","https://openalex.org/W2965407115","https://openalex.org/W2995481444","https://openalex.org/W2996896271","https://openalex.org/W3016507688","https://openalex.org/W3046093665","https://openalex.org/W3046814132","https://openalex.org/W3087549734","https://openalex.org/W3096726323","https://openalex.org/W3097816393","https://openalex.org/W3107153805","https://openalex.org/W3117215073","https://openalex.org/W3139377883","https://openalex.org/W3141797743","https://openalex.org/W3178094535","https://openalex.org/W3207318282","https://openalex.org/W4214717370","https://openalex.org/W4225619352","https://openalex.org/W4229060449","https://openalex.org/W4280508537","https://openalex.org/W4292022450","https://openalex.org/W4295177675","https://openalex.org/W4296935478","https://openalex.org/W4310336120","https://openalex.org/W4312327301","https://openalex.org/W4315588599","https://openalex.org/W4319988532","https://openalex.org/W6678007500","https://openalex.org/W6679661297","https://openalex.org/W6704571135","https://openalex.org/W6732837357","https://openalex.org/W6740804295","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6751346906","https://openalex.org/W6755950020","https://openalex.org/W6756754374","https://openalex.org/W6757223306","https://openalex.org/W6765652072","https://openalex.org/W6766799311","https://openalex.org/W6769596995","https://openalex.org/W6779771741","https://openalex.org/W6780779400","https://openalex.org/W6783292247","https://openalex.org/W6783953898","https://openalex.org/W6785535465","https://openalex.org/W6791110673","https://openalex.org/W6795534454","https://openalex.org/W6803116530","https://openalex.org/W6803290710","https://openalex.org/W6843222607","https://openalex.org/W6849153783","https://openalex.org/W6849896277"],"related_works":["https://openalex.org/W1687432146","https://openalex.org/W1591874556","https://openalex.org/W2185608106","https://openalex.org/W3046258185","https://openalex.org/W1548083239","https://openalex.org/W3216994056","https://openalex.org/W2268232908","https://openalex.org/W205610463","https://openalex.org/W4296050054","https://openalex.org/W2893240344"],"abstract_inverted_index":{"A":[0],"key":[1],"challenge":[2],"of":[3,33,65,75,94,110,135,228],"continual":[4,50],"reinforcement":[5,16],"learning":[6,17],"(CRL)":[7],"in":[8,41,68,172,226],"dynamic":[9,70],"environments":[10],"is":[11,185],"to":[12,85,121,125,168],"promptly":[13],"adapt":[14],"the":[15,22,30,34,69,87,127,133,147,189,201],"(RL)":[18],"agent's":[19],"behavior":[20],"as":[21,99,107,150,160,235],"environment":[23,71,118],"changes":[24,171],"over":[25,130,223],"its":[26],"lifetime":[27],"while":[28],"minimizing":[29],"catastrophic":[31],"forgetting":[32],"learned":[35,204],"information.":[36],"To":[37],"address":[38],"this":[39,42,142],"challenge,":[40],"article,":[43],"we":[44,90,175],"propose":[45],"DaCoRL,":[46],"that":[47,210],"is,":[48],"dynamics-adaptive":[49],"RL.":[51],"DaCoRL":[52,219],"learns":[53],"a":[54,63,73,92,108,136,151,157,194,207],"context-conditioned":[55],"policy":[56],"using":[57],"progressive":[58],"contextualization,":[59],"which":[60],"incrementally":[61],"clusters":[62],"stream":[64],"stationary":[66],"tasks":[67,95],"into":[72],"series":[74],"contexts":[76],"and":[77,103,193,232,244],"opts":[78],"for":[79,199],"an":[80,100,177],"expandable":[81,178],"multihead":[82,179],"neural":[83,180],"network":[84,181],"approximate":[86],"policy.":[88],"Specifically,":[89],"define":[91],"set":[93],"with":[96,188,214],"similar":[97],"dynamics":[98],"environmental":[101,170],"context":[102,105,154,159,192],"formalize":[104],"inference":[106,124],"procedure":[109],"online":[111,122],"Bayesian":[112,123],"infinite":[113],"Gaussian":[114],"mixture":[115],"clustering":[116],"on":[117,164,203,240],"features,":[119],"resorting":[120],"infer":[126],"posterior":[128],"distribution":[129],"contexts.":[131],"Under":[132],"assumption":[134],"Chinese":[137],"restaurant":[138],"process":[139],"(CRP)":[140],"prior,":[141],"technique":[143],"can":[144,211],"accurately":[145],"classify":[146],"current":[148],"task":[149],"previously":[152],"seen":[153],"or":[155],"instantiate":[156],"new":[158],"needed":[161],"without":[162],"relying":[163],"any":[165],"external":[166],"indicator":[167],"signal":[169],"advance.":[173],"Furthermore,":[174],"employ":[176],"whose":[182],"output":[183],"layer":[184],"synchronously":[186],"expanded":[187],"newly":[190],"instantiated":[191],"knowledge":[195],"distillation":[196],"regularization":[197],"term":[198],"retaining":[200],"performance":[202],"tasks.":[205,247],"As":[206],"general":[208],"framework":[209],"be":[212],"coupled":[213],"various":[215],"deep":[216],"RL":[217],"algorithms,":[218],"features":[220],"consistent":[221],"superiority":[222],"existing":[224],"methods":[225],"terms":[227],"stability,":[229],"overall":[230],"performance,":[231],"generalization":[233],"ability,":[234],"verified":[236],"by":[237],"extensive":[238],"experiments":[239],"several":[241],"robot":[242],"navigation":[243],"MuJoCo":[245],"locomotion":[246]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}