{"id":"https://openalex.org/W4389326757","doi":"https://doi.org/10.1109/tcds.2023.3338241","title":"A Brain-Inspired Incremental Multitask Reinforcement Learning Approach","display_name":"A Brain-Inspired Incremental Multitask Reinforcement Learning Approach","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4389326757","doi":"https://doi.org/10.1109/tcds.2023.3338241"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2023.3338241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2023.3338241","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental 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/A5102759759","display_name":"Changyuan Jin","orcid":"https://orcid.org/0009-0003-3085-4250"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenying Jin","raw_affiliation_strings":["East China University of Science and Technology, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050493033","display_name":"Xiang Feng","orcid":"https://orcid.org/0000-0001-6083-3440"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Feng","raw_affiliation_strings":["East China University of Science and Technology, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058941949","display_name":"Huiqun Yu","orcid":"https://orcid.org/0000-0002-1899-1135"},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiqun Yu","raw_affiliation_strings":["East China University of Science and Technology, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China University of Science and Technology, Shanghai, China","institution_ids":["https://openalex.org/I143593769"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102759759"],"corresponding_institution_ids":["https://openalex.org/I143593769"],"apc_list":null,"apc_paid":null,"fwci":0.5245,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72620905,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"16","issue":"3","first_page":"1147","last_page":"1160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9958000183105469,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9926999807357788,"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/computer-science","display_name":"Computer science","score":0.8819658160209656},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8400524854660034},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7398993372917175},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5546377301216125},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5516230463981628},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5049610733985901},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.4484427869319916},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.43530386686325073},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.393553227186203}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8819658160209656},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8400524854660034},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7398993372917175},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5546377301216125},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5516230463981628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5049610733985901},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.4484427869319916},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43530386686325073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.393553227186203},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2023.3338241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2023.3338241","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2570400918","display_name":null,"funder_award_id":"2020YFB1711700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4157426647","display_name":null,"funder_award_id":"62372174","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G686699220","display_name":null,"funder_award_id":"62276097","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W196761320","https://openalex.org/W1658008008","https://openalex.org/W2012060221","https://openalex.org/W2092886985","https://openalex.org/W2110422826","https://openalex.org/W2134243390","https://openalex.org/W2136435696","https://openalex.org/W2194775991","https://openalex.org/W2516955577","https://openalex.org/W2614358123","https://openalex.org/W2616729100","https://openalex.org/W2738724892","https://openalex.org/W2761873684","https://openalex.org/W2792645523","https://openalex.org/W2891076394","https://openalex.org/W2952687353","https://openalex.org/W2963095800","https://openalex.org/W2963674921","https://openalex.org/W2997756730","https://openalex.org/W3081310128","https://openalex.org/W3121078556","https://openalex.org/W3129936460","https://openalex.org/W4200438872","https://openalex.org/W4210907107","https://openalex.org/W4211122488","https://openalex.org/W4213328554","https://openalex.org/W4214717370","https://openalex.org/W4292794805","https://openalex.org/W4297797010","https://openalex.org/W4298174377","https://openalex.org/W4298857966","https://openalex.org/W6608133726","https://openalex.org/W6636881020","https://openalex.org/W6637967152","https://openalex.org/W6685726866","https://openalex.org/W6692846177","https://openalex.org/W6713348437","https://openalex.org/W6715102896","https://openalex.org/W6718190810","https://openalex.org/W6730111887","https://openalex.org/W6734655788","https://openalex.org/W6738023940","https://openalex.org/W6738174457","https://openalex.org/W6740879895","https://openalex.org/W6747473740","https://openalex.org/W6748638692","https://openalex.org/W6775647304","https://openalex.org/W6780559895","https://openalex.org/W6910546390"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2389214306","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Recently,":[0],"there":[1],"have":[2,140],"been":[3],"growing":[4],"interests":[5],"in":[6,28,73,105,134,172],"multitask":[7],"reinforcement":[8],"learning":[9,71],"(MTRL),":[10],"which":[11],"is":[12],"viewed":[13],"as":[14,117],"a":[15,50,118,145,169],"promising":[16],"framework":[17],"for":[18,35,125],"training":[19],"agents":[20],"to":[21,40,61,107,180],"execute":[22],"multiple":[23,67],"tasks":[24,133],"simultaneously.":[25],"However,":[26],"limitations":[27],"scalability":[29,65,171],"and":[30,42,64,79,94,120,138,150,161,175,185],"convergence":[31,110],"remain":[32],"key":[33],"obstacles":[34],"scaling":[36],"these":[37,102],"MTRL":[38],"algorithms":[39],"dynamic":[41],"complex":[43],"tasks.":[44,68],"To":[45],"address":[46],"these,":[47],"we":[48,76,112],"propose":[49],"method":[51,116],"called":[52],"Brain-inspired":[53],"Incremental":[54],"Multi-Task":[55],"Reinforcement":[56],"Learning":[57],"(BIMTRL)":[58],"that":[59,142],"aims":[60],"improve":[62],"parallelism":[63],"of":[66,86,91],"Inspired":[69],"by":[70],"processes":[72],"human":[74],"brain,":[75],"integrate":[77],"conscious":[78],"subconscious":[80],"modes":[81],"into":[82],"the":[83,109,114,165],"agents\u2019":[84],"exploration":[85],"environments.":[87],"Our":[88],"two-step":[89],"strategy":[90],"policy":[92],"loosening":[93],"importance":[95],"trade-off":[96],"enables":[97],"an":[98],"effective":[99],"switch":[100],"between":[101],"modes.":[103],"Additionally,":[104],"order":[106],"overcome":[108],"dilemma,":[111],"adopt":[113],"V-trace":[115],"stable":[119],"robust":[121],"off-policy":[122],"correction":[123],"technique":[124],"our":[126],"actor-critic":[127],"agents.":[128],"Experimental":[129],"evaluations":[130],"on":[131],"various":[132],"OpenAI":[135],"Gym,":[136],"Atari":[137],"PyBullet":[139],"demonstrated":[141],"BIMTRL":[143,166],"achieves":[144],"61.4%":[146],"greater":[147],"average":[148],"return":[149],"57.6%":[151],"higher":[152,183],"speed":[153],"than":[154],"specific":[155],"multi-task":[156],"baselines.":[157],"Furthermore,":[158],"its":[159],"distributed":[160],"incremental":[162],"architecture":[163],"endows":[164],"approach":[167],"with":[168],"desired":[170],"both":[173],"discrete":[174],"continuous":[176],"environments,":[177],"ultimately":[178],"leading":[179],"larger":[181],"rewards,":[182],"speed,":[184],"better":[186],"convergence.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}