{"id":"https://openalex.org/W4407736288","doi":"https://doi.org/10.1109/tcds.2025.3543694","title":"Efficient Multitask Reinforcement Learning via Task-Specific Action Correction","display_name":"Efficient Multitask Reinforcement Learning via Task-Specific Action Correction","publication_year":2025,"publication_date":"2025-02-19","ids":{"openalex":"https://openalex.org/W4407736288","doi":"https://doi.org/10.1109/tcds.2025.3543694"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2025.3543694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3543694","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":true,"oa_status":"green","oa_url":"https://purehost.bath.ac.uk/ws/files/360367940/TCDS_TSAC.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026032007","display_name":"Jinyuan Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinyuan Feng","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-8048-1112","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Min Chen","orcid":"https://orcid.org/0000-0003-1938-2603"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Chen","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1938-2603","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060319097","display_name":"Zhiqiang Pu","orcid":"https://orcid.org/0000-0002-4841-4048"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Pu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4841-4048","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043281824","display_name":"Tenghai Qiu","orcid":"https://orcid.org/0000-0002-0312-5728"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tenghai Qiu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0312-5728","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019541846","display_name":"Jianqiang Yi","orcid":"https://orcid.org/0000-0003-3268-9482"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Yi","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3268-9482","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0002-5348-7671"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I51601045","display_name":"University of Bath","ror":"https://ror.org/002h8g185","country_code":"GB","type":"education","lineage":["https://openalex.org/I51601045"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["Department of Computer Science, University of Bath, Bath, U.K","Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5348-7671","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Bath, Bath, U.K","institution_ids":["https://openalex.org/I51601045"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5026032007"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"],"apc_list":null,"apc_paid":null,"fwci":6.5198,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95666557,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"17","issue":"5","first_page":"1110","last_page":"1124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9488000273704529,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9488000273704529,"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":0.9373000264167786,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9164999723434448,"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/computer-science","display_name":"Computer science","score":0.8507941961288452},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.767136812210083},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7083138227462769},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49100473523139954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43149739503860474},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4208359718322754},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3959716856479645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8507941961288452},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.767136812210083},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7083138227462769},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49100473523139954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43149739503860474},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4208359718322754},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3959716856479645},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/tcds.2025.3543694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3543694","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"},{"id":"pmh:oai:purehost.bath.ac.uk:openaire/c35a4f25-a2ad-41e5-bed0-f7870b876fab","is_oa":true,"landing_page_url":"https://researchportal.bath.ac.uk/en/publications/c35a4f25-a2ad-41e5-bed0-f7870b876fab","pdf_url":"https://purehost.bath.ac.uk/ws/files/360367940/TCDS_TSAC.pdf","source":{"id":"https://openalex.org/S4377196294","display_name":"Pure (University of Bath)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I51601045","host_organization_name":"University of Bath","host_organization_lineage":["https://openalex.org/I51601045"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Feng, J, Chen, M, Pu, Z, Qiu, T, Yi, J & Zhang, J 2025, 'Efficient Multi-Task Reinforcement Learning via Task-Specific Action Correction', IEEE Transactions on Cognitive and Developmental Systems. https://doi.org/10.1109/TCDS.2025.3543694","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:purehost.bath.ac.uk:openaire/c35a4f25-a2ad-41e5-bed0-f7870b876fab","is_oa":true,"landing_page_url":"https://researchportal.bath.ac.uk/en/publications/c35a4f25-a2ad-41e5-bed0-f7870b876fab","pdf_url":"https://purehost.bath.ac.uk/ws/files/360367940/TCDS_TSAC.pdf","source":{"id":"https://openalex.org/S4377196294","display_name":"Pure (University of Bath)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I51601045","host_organization_name":"University of Bath","host_organization_lineage":["https://openalex.org/I51601045"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Feng, J, Chen, M, Pu, Z, Qiu, T, Yi, J & Zhang, J 2025, 'Efficient Multi-Task Reinforcement Learning via Task-Specific Action Correction', IEEE Transactions on Cognitive and Developmental Systems. https://doi.org/10.1109/TCDS.2025.3543694","raw_type":"article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1552939569","display_name":null,"funder_award_id":"20220484077","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"},{"id":"https://openalex.org/G5354033369","display_name":null,"funder_award_id":"20230484435","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"},{"id":"https://openalex.org/G6672390475","display_name":null,"funder_award_id":"62322316","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/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407736288.pdf","grobid_xml":"https://content.openalex.org/works/W4407736288.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2131600418","https://openalex.org/W2766447205","https://openalex.org/W2803208334","https://openalex.org/W2964335674","https://openalex.org/W2973229164","https://openalex.org/W2982316857","https://openalex.org/W2995918197","https://openalex.org/W3022652760","https://openalex.org/W3208335691","https://openalex.org/W4205536455","https://openalex.org/W4206026943","https://openalex.org/W4206149971","https://openalex.org/W4231341614","https://openalex.org/W4293143512","https://openalex.org/W4310336120","https://openalex.org/W4312548104","https://openalex.org/W4321195193","https://openalex.org/W4376269829","https://openalex.org/W4386736782","https://openalex.org/W4386883554","https://openalex.org/W4389326757","https://openalex.org/W4390120052","https://openalex.org/W4393147301","https://openalex.org/W4398226357","https://openalex.org/W4402727783","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W3196817267","https://openalex.org/W1976600725","https://openalex.org/W1564680838","https://openalex.org/W2003125260","https://openalex.org/W2060591604","https://openalex.org/W1992291644","https://openalex.org/W2166791242","https://openalex.org/W2585162246","https://openalex.org/W1934413089","https://openalex.org/W2098419343"],"abstract_inverted_index":{"Multitask":[0],"reinforcement":[1,56],"learning":[2,46,122],"(MTRL)":[3],"holds":[4],"potential":[5,74],"for":[6,32],"building":[7],"general-purpose":[8],"agents,":[9],"enabling":[10,168],"them":[11],"to":[12,25,41,106,111,171,176,202],"generalize":[13],"across":[14,48,184,241],"a":[15,37,66,88,127,140,173,178,204],"variety":[16],"of":[17,68,83],"tasks.":[18,28,185,242],"However,":[19],"MTRL":[20,108],"may":[21],"still":[22],"be":[23],"susceptible":[24],"conflicts":[26,76,151],"between":[27],"A":[29],"primary":[30],"reason":[31],"this":[33],"problem":[34],"is":[35],"that":[36,207,224],"universal":[38],"policy":[39,121,129,135],"struggles":[40],"balance":[42],"short-term":[43,75,141],"and":[44,90,119,131,181,192,217,237],"dense":[45,147],"signals":[47],"various":[49],"tasks,":[50],"e.g.,":[51],"distinct":[52],"reward":[53],"functions":[54],"in":[55,77,160,233],"learning.":[57],"In":[58],"social":[59],"cognitive":[60,69],"theory,":[61],"internalized":[62],"future":[63,84],"goals,":[64,85],"as":[65,102],"form":[67,203],"representations,":[70],"can":[71],"effectively":[72],"mitigate":[73],"multitask":[78,218],"settings.":[79],"Considering":[80],"the":[81,99,162,187,198,210],"benefits":[82],"we":[86],"propose":[87],"novel":[89],"general":[91],"framework":[92],"called":[93],"task-specific":[94],"action":[95,133,143,180,199,206,239],"correction":[96,134,179,200],"(TSAC)":[97],"from":[98,153],"goal":[100],"perspective":[101,142,175],"an":[103,132,169],"orthogonal":[104],"research":[105],"previous":[107],"methods.":[109],"Specifically,":[110],"avoid":[112],"myopia,":[113],"TSAC":[114,225],"introduces":[115],"goal-oriented":[116,165],"sparse":[117,166],"rewards":[118],"decomposes":[120],"into":[123],"two":[124],"separate":[125],"policies:":[126],"shared":[128],"(SP)":[130],"(ACP).":[136],"The":[137],"SP":[138,191],"outputs":[139],"based":[144,196],"on":[145,156,197,215],"guiding":[146],"rewards.":[148],"To":[149],"alleviate":[150],"resulting":[152],"excessive":[154],"focus":[155],"specific":[157],"tasks\u2019":[158],"details":[159],"SP,":[161],"ACP":[163,193],"incorporates":[164],"rewards,":[167],"agent":[170],"adopt":[172],"long-term":[174],"output":[177,189],"achieve":[182],"generalization":[183,236],"Finally,":[186],"actions":[188],"by":[190],"are":[194],"combined":[195],"function":[201],"final":[205],"interact":[208],"with":[209],"environment.":[211],"Extensive":[212],"experiments":[213],"conducted":[214],"meta-world":[216],"StarCraft":[219],"II":[220],"multiagent":[221],"scenarios":[222],"demonstrate":[223],"outperforms":[226],"existing":[227],"state-of-the-art":[228],"methods,":[229],"achieving":[230],"significant":[231],"improvements":[232],"sample":[234],"efficiency,":[235],"effective":[238],"execution":[240]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}