{"id":"https://openalex.org/W4391791543","doi":"https://doi.org/10.1109/tcyb.2024.3356981","title":"Deep Reinforcement Learning in Nonstationary Environments With Unknown Change Points","display_name":"Deep Reinforcement Learning in Nonstationary Environments With Unknown Change Points","publication_year":2024,"publication_date":"2024-02-13","ids":{"openalex":"https://openalex.org/W4391791543","doi":"https://doi.org/10.1109/tcyb.2024.3356981","pmid":"https://pubmed.ncbi.nlm.nih.gov/38349837"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2024.3356981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2024.3356981","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","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/A5073161629","display_name":"Z. Q. Liu","orcid":"https://orcid.org/0000-0003-3624-7753"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Zihe Liu","raw_affiliation_strings":["Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3624-7753","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675577","display_name":"Jie L\u00fc","orcid":"https://orcid.org/0000-0003-0690-4732"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jie Lu","raw_affiliation_strings":["Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0690-4732","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029498647","display_name":"Junyu Xuan","orcid":"https://orcid.org/0000-0002-8367-6908"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Junyu Xuan","raw_affiliation_strings":["Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8367-6908","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062192039","display_name":"Guangquan Zhang","orcid":"https://orcid.org/0000-0003-3960-0583"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guangquan Zhang","raw_affiliation_strings":["Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3960-0583","affiliations":[{"raw_affiliation_string":"Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073161629"],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":2.6491,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90551572,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"54","issue":"9","first_page":"5191","last_page":"5204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9887999892234802,"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":0.9887999892234802,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9081000089645386,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.8331646919250488},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.671062707901001},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6481412649154663},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5691593885421753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5445693731307983},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.5327005386352539},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.49687889218330383},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4650273323059082},{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.4128299653530121},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3137568533420563}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8331646919250488},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.671062707901001},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6481412649154663},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5691593885421753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5445693731307983},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.5327005386352539},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.49687889218330383},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4650273323059082},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.4128299653530121},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3137568533420563},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2024.3356981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2024.3356981","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:38349837","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38349837","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 cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5272666880","display_name":null,"funder_award_id":"DE200100245","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G6774349052","display_name":null,"funder_award_id":"FL190100149","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W2007376249","https://openalex.org/W2079054072","https://openalex.org/W2115524942","https://openalex.org/W2145339207","https://openalex.org/W2152670157","https://openalex.org/W2554616628","https://openalex.org/W2560647685","https://openalex.org/W2736601468","https://openalex.org/W2767278854","https://openalex.org/W2901747954","https://openalex.org/W2921236134","https://openalex.org/W2943927637","https://openalex.org/W2954033048","https://openalex.org/W2963948533","https://openalex.org/W2964254877","https://openalex.org/W2967474307","https://openalex.org/W2995912970","https://openalex.org/W3046814132","https://openalex.org/W3093655779","https://openalex.org/W3117215073","https://openalex.org/W3168573009","https://openalex.org/W3199468096","https://openalex.org/W3205801758","https://openalex.org/W4251448363","https://openalex.org/W4283365039","https://openalex.org/W4292973684","https://openalex.org/W4319988532","https://openalex.org/W4383112908","https://openalex.org/W6683204974","https://openalex.org/W6688325169","https://openalex.org/W6692846177","https://openalex.org/W6738602802","https://openalex.org/W6740804295","https://openalex.org/W6741002519","https://openalex.org/W6741087337","https://openalex.org/W6741217325","https://openalex.org/W6751591294","https://openalex.org/W6752495264","https://openalex.org/W6760539816","https://openalex.org/W6760698134","https://openalex.org/W6771208548","https://openalex.org/W6771876938","https://openalex.org/W6773641948","https://openalex.org/W6777493926","https://openalex.org/W6780298656","https://openalex.org/W6780559895","https://openalex.org/W6790463934","https://openalex.org/W6796062334","https://openalex.org/W6801111356","https://openalex.org/W6803156713","https://openalex.org/W6846105488","https://openalex.org/W6849896277"],"related_works":["https://openalex.org/W4229448053","https://openalex.org/W4247925126","https://openalex.org/W4327774218","https://openalex.org/W2059768187","https://openalex.org/W4312858960","https://openalex.org/W4386036939","https://openalex.org/W4379143281","https://openalex.org/W2605096541","https://openalex.org/W3200286695","https://openalex.org/W4386322305"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,9],"(DRL)":[3],"is":[4,65,83,178],"a":[5,13,102],"powerful":[6],"tool":[7],"for":[8,49,106,191],"from":[10],"interactions":[11],"within":[12],"stationary":[14],"environment":[15],"where":[16],"state":[17,36],"transition":[18,37],"and":[19,52,73,92,126,153,177,204],"reward":[20,39,173],"distributions":[21],"remain":[22],"constant":[23],"throughout":[24],"the":[25,28,43,50,67,71,74,121,136,139,143,156,167,171,179,193],"process.":[26],"Addressing":[27],"practical":[29],"but":[30],"challenging":[31],"nonstationary":[32,63,107],"environments":[33,64,76,108],"with":[34,62,109,142],"time-varying":[35],"or":[38],"function":[40],"changes":[41],"during":[42],"interactions,":[44],"ingenious":[45],"solutions":[46],"are":[47,77],"essential":[48],"stability":[51],"robustness":[53],"of":[54,124,138,146,196],"DRL":[55,104],"agents.":[56],"A":[57,128],"key":[58],"assumption":[59,82],"to":[60,161,181,183],"cope":[61],"that":[66,166],"change":[68,111,117],"points":[69,118],"between":[70],"previous":[72,151],"new":[75,184],"known":[78],"beforehand.":[79],"Unfortunately,":[80],"this":[81,97,99],"impractical":[84],"in":[85],"many":[86],"cases,":[87],"such":[88,199],"as":[89,200],"outdoor":[90],"robots":[91],"online":[93],"recommendations.":[94],"To":[95],"address":[96],"problem,":[98],"article":[100],"presents":[101],"robust":[103],"algorithm":[105,114],"unknown":[110],"points.":[112],"The":[113,150],"actively":[115],"detects":[116],"by":[119],"monitoring":[120],"joint":[122],"distribution":[123],"states":[125],"actions.":[127],"detection":[129],"boosted,":[130],"gradient-constrained":[131],"optimization":[132],"method":[133,169],"then":[134],"adapts":[135],"training":[137],"current":[140,157],"policy":[141,158],"supporting":[144],"knowledge":[145],"formerly":[147],"well-trained":[148],"policies.":[149],"policies":[152],"experience":[154],"help":[155],"adapt":[159,182],"rapidly":[160],"environmental":[162,194],"changes.":[163],"Experiments":[164],"show":[165],"proposed":[168],"accumulates":[170],"highest":[172],"among":[174],"several":[175],"alternatives":[176],"fastest":[180],"environments.":[185],"This":[186],"work":[187],"has":[188],"compelling":[189],"potential":[190],"increasing":[192],"suitability":[195],"intelligent":[197],"agents,":[198],"drones,":[201],"autonomous":[202],"vehicles,":[203],"underwater":[205],"robots.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}