{"id":"https://openalex.org/W4407638197","doi":"https://doi.org/10.1109/tsmc.2025.3537990","title":"A Unified Sparse Training Framework for Lightweight Lifelong Deep Reinforcement Learning","display_name":"A Unified Sparse Training Framework for Lightweight Lifelong Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-02-17","ids":{"openalex":"https://openalex.org/W4407638197","doi":"https://doi.org/10.1109/tsmc.2025.3537990"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2025.3537990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3537990","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"},"type":"article","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/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":"middle","author":{"id":"https://openalex.org/A5111335760","display_name":"Weiwei Fu","orcid":null},"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":"Weiwei Fu","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":null,"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/A5112392402","display_name":"Y.S. Lin","orcid":"https://orcid.org/0009-0005-2109-3829"},"institutions":[{"id":"https://openalex.org/I4210113837","display_name":"Taiwan Forestry Research Institute","ror":"https://ror.org/01d34a364","country_code":"TW","type":"facility","lineage":["https://openalex.org/I26359584","https://openalex.org/I4210113837"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Rong Lin","raw_affiliation_strings":["AI Research Center, Hon Hai Research Institute, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0009-0005-2109-3829","affiliations":[{"raw_affiliation_string":"AI Research Center, Hon Hai Research Institute, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210113837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048205934","display_name":"Yung\u2010Hui Li","orcid":"https://orcid.org/0000-0002-0475-3689"},"institutions":[{"id":"https://openalex.org/I4210113837","display_name":"Taiwan Forestry Research Institute","ror":"https://ror.org/01d34a364","country_code":"TW","type":"facility","lineage":["https://openalex.org/I26359584","https://openalex.org/I4210113837"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yung-Hui Li","raw_affiliation_strings":["AI Research Center, Hon Hai Research Institute, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-0475-3689","affiliations":[{"raw_affiliation_string":"AI Research Center, Hon Hai Research Institute, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210113837"]}]},{"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":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82293526,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"55","issue":"4","first_page":"2998","last_page":"3012"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.864300012588501,"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":0.864300012588501,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.847000002861023,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10784","display_name":"Muscle activation and electromyography studies","score":0.7781000137329102,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.7464381456375122},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6941109299659729},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6570526957511902},{"id":"https://openalex.org/keywords/lifelong-learning","display_name":"Lifelong learning","score":0.6518413424491882},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5814574360847473},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4113544821739197},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1472562551498413},{"id":"https://openalex.org/keywords/pedagogy","display_name":"Pedagogy","score":0.08024603128433228},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.038398414850234985}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7464381456375122},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6941109299659729},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6570526957511902},{"id":"https://openalex.org/C108771440","wikidata":"https://www.wikidata.org/wiki/Q368475","display_name":"Lifelong learning","level":2,"score":0.6518413424491882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5814574360847473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4113544821739197},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1472562551498413},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.08024603128433228},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.038398414850234985},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2025.3537990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3537990","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"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/G7643524006","display_name":null,"funder_award_id":"R5060-19","funder_id":"https://openalex.org/F4320322887","funder_display_name":"The Research Council"}],"funders":[{"id":"https://openalex.org/F4320322887","display_name":"The Research Council","ror":"https://ror.org/03tcppy59"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2560647685","https://openalex.org/W2978696242","https://openalex.org/W2999204576","https://openalex.org/W3042228527","https://openalex.org/W3046814132","https://openalex.org/W3048941751","https://openalex.org/W3091958244","https://openalex.org/W3117215073","https://openalex.org/W3127177108","https://openalex.org/W3202264206","https://openalex.org/W4280508537","https://openalex.org/W4285600354","https://openalex.org/W4385863710","https://openalex.org/W4391131278","https://openalex.org/W4392668879","https://openalex.org/W4396506409","https://openalex.org/W4405877891","https://openalex.org/W6687681856","https://openalex.org/W6726983090","https://openalex.org/W6771838272","https://openalex.org/W6772129282","https://openalex.org/W6783674534","https://openalex.org/W6792049622","https://openalex.org/W6802227391","https://openalex.org/W6802999184","https://openalex.org/W6810594387","https://openalex.org/W6838929685","https://openalex.org/W6839330762","https://openalex.org/W6843138321","https://openalex.org/W6844961931","https://openalex.org/W6846406187","https://openalex.org/W6849777495","https://openalex.org/W6850175866","https://openalex.org/W6853588135","https://openalex.org/W6855821840","https://openalex.org/W6858732062","https://openalex.org/W6860732124"],"related_works":["https://openalex.org/W2364105709","https://openalex.org/W2384383462","https://openalex.org/W2380954666","https://openalex.org/W422428167","https://openalex.org/W1981922029","https://openalex.org/W2037025106","https://openalex.org/W2499777278","https://openalex.org/W2391851613","https://openalex.org/W1485190762","https://openalex.org/W4372778609"],"abstract_inverted_index":{"Lifelong":[0],"deep":[1],"reinforcement":[2],"learning":[3],"(DRL)":[4],"methods":[5,19,68,85,178],"enable":[6],"continuous":[7],"adaptation":[8],"to":[9,26,47,54,69,94,127,142,188,195],"new":[10],"tasks":[11],"and":[12,29,35,105,146,184],"retention":[13],"of":[14,73,102,132],"old":[15],"knowledge.":[16],"However,":[17],"these":[18],"often":[20],"necessitate":[21],"large":[22],"model":[23,134,148],"sizes,":[24],"leading":[25],"substantial":[27],"computational":[28,138],"storage":[30],"resource":[31],"requirements":[32],"during":[33],"training":[34,83],"inference.":[36],"Unfortunately,":[37],"existing":[38,65],"research":[39],"has":[40],"not":[41],"yet":[42],"provided":[43],"a":[44,56,118,152],"lightweight":[45,74,96],"solution":[46],"address":[48],"this":[49],"issue.":[50],"This":[51],"work":[52],"aims":[53],"develop":[55,117],"generic":[57],"method":[58,121],"that":[59,122,155,167],"can":[60],"be":[61],"seamlessly":[62],"integrated":[63],"into":[64],"lifelong":[66,111,176],"DRL":[67,92,177],"facilitate":[70],"their":[71],"achievement":[72],"models":[75],"while":[76,179],"also":[77],"yielding":[78],"higher":[79,181],"returns.":[80],"While":[81],"sparse":[82],"(ST)":[84],"have":[86],"been":[87],"extensively":[88],"used":[89],"in":[90,110,173],"the":[91,100,129,133,161,196],"community":[93],"achieve":[95],"models,":[97],"they":[98],"exacerbate":[99],"issue":[101],"catastrophic":[103,144],"forgetting":[104,145],"compromise":[106],"generalization":[107],"when":[108],"applied":[109],"DRL.":[112],"To":[113],"improve":[114],"generalization,":[115],"we":[116,150],"gradient":[119,130],"optimization":[120],"leverages":[123],"sharpness-aware":[124],"minimization":[125],"(SAM)":[126],"smooth":[128],"surface":[131],"without":[135],"introducing":[136],"excessive":[137],"complexity.":[139],"In":[140],"addition,":[141],"alleviate":[143],"promote":[147],"convergence,":[149],"introduce":[151],"priority-based":[153],"approach":[154,169],"samples":[156],"effective":[157],"past":[158],"experiences":[159],"from":[160],"replay":[162],"buffer.":[163],"Extensive":[164],"experiments":[165],"demonstrate":[166],"our":[168],"achieves":[170],"90%":[171],"sparsity":[172],"five":[174],"representative":[175],"achieving":[180],"episode":[182],"return":[183,186],"average":[185],"(up":[187],"34%":[189],"improvement)":[190],"across":[191],"all":[192],"episodes":[193],"compared":[194],"dense":[197],"models.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}