{"id":"https://openalex.org/W4376269829","doi":"https://doi.org/10.1109/lra.2023.3271445","title":"Multi-Task Reinforcement Learning With Attention-Based Mixture of Experts","display_name":"Multi-Task Reinforcement Learning With Attention-Based Mixture of Experts","publication_year":2023,"publication_date":"2023-05-12","ids":{"openalex":"https://openalex.org/W4376269829","doi":"https://doi.org/10.1109/lra.2023.3271445"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3271445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3271445","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5101632944","display_name":"Guangran Cheng","orcid":"https://orcid.org/0000-0003-0865-532X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guangran Cheng","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-0865-532X","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088413924","display_name":"Lu Dong","orcid":"https://orcid.org/0000-0001-6737-1381"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Dong","raw_affiliation_strings":["School of Cyber Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-6737-1381","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059258252","display_name":"Wenzhe Cai","orcid":"https://orcid.org/0000-0003-4610-3454"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhe Cai","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4610-3454","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019248683","display_name":"Changyin Sun","orcid":"https://orcid.org/0000-0001-9269-334X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyin Sun","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9269-334X","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101632944"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":4.2602,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.95297632,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"8","issue":"6","first_page":"3812","last_page":"3819"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9904000163078308,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9878000020980835,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8642894625663757},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7668842077255249},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.743408203125},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6420178413391113},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5888988375663757},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5547990798950195},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.5249069929122925},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4420914351940155},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07477056980133057}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8642894625663757},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7668842077255249},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.743408203125},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6420178413391113},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5888988375663757},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5547990798950195},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.5249069929122925},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4420914351940155},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07477056980133057},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3271445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3271445","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5033343354","display_name":null,"funder_award_id":"61921004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G745626259","display_name":null,"funder_award_id":"62236002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8877631286","display_name":null,"funder_award_id":"62173251","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2025653905","https://openalex.org/W2145339207","https://openalex.org/W2150884987","https://openalex.org/W2735995851","https://openalex.org/W2736601468","https://openalex.org/W2781726626","https://openalex.org/W2809290718","https://openalex.org/W2891076394","https://openalex.org/W2902347140","https://openalex.org/W2920362155","https://openalex.org/W2963216850","https://openalex.org/W2963864421","https://openalex.org/W2965373594","https://openalex.org/W2981344907","https://openalex.org/W2991309414","https://openalex.org/W2995481444","https://openalex.org/W2996490626","https://openalex.org/W3013821552","https://openalex.org/W3022652760","https://openalex.org/W3033503043","https://openalex.org/W3087931390","https://openalex.org/W3106539628","https://openalex.org/W3141797743","https://openalex.org/W3212494843","https://openalex.org/W4285066157","https://openalex.org/W4287329474","https://openalex.org/W4293370597","https://openalex.org/W4298174377","https://openalex.org/W4313178149","https://openalex.org/W4385245566","https://openalex.org/W6684921986","https://openalex.org/W6685726866","https://openalex.org/W6739901393","https://openalex.org/W6740879895","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6756732229","https://openalex.org/W6760405395","https://openalex.org/W6766673545","https://openalex.org/W6769596995","https://openalex.org/W6770205404","https://openalex.org/W6771876938","https://openalex.org/W6771912484","https://openalex.org/W6775647304","https://openalex.org/W6779247072","https://openalex.org/W6790190981","https://openalex.org/W6803156713"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2372385138","https://openalex.org/W2951720331"],"abstract_inverted_index":{"Multi-task":[0],"learning":[1,63,154],"is":[2],"an":[3,56,95],"important":[4],"problem":[5],"in":[6,38,81,147],"reinforcement":[7,62,153],"learning.":[8,31],"Training":[9],"multiple":[10],"tasks":[11,22,102,170],"together":[12],"brings":[13],"benefits":[14],"from":[15,119],"the":[16,39,90,107,133,161],"shared":[17],"useful":[18],"information":[19],"across":[20,44,51],"different":[21,82,169],"and":[23,103,123,141,160],"often":[24],"achieves":[25],"higher":[26],"performance":[27,109,143],"compared":[28],"to":[29,65,98,105,136],"single-task":[30],"However,":[32],"it":[33],"remains":[34],"unclear":[35],"how":[36],"parameters":[37,50],"network":[40],"should":[41],"be":[42],"reused":[43],"tasks.":[45],"Instead":[46],"of":[47,59,84],"naively":[48],"sharing":[49],"all":[52],"tasks,":[53,159],"we":[54,93],"propose":[55,94],"attention-based":[57],"mixture":[58],"experts":[60,104],"multi-task":[61,85,152,162],"approach":[64,113,135],"learn":[66,76,116],"a":[67,149],"compositional":[68],"policy":[69],"for":[70,151],"each":[71],"task.":[72],"The":[73,111],"expert":[74,91,129],"networks":[75],"task-specific":[77],"skills":[78],"which":[79,165],"specialize":[80],"parts":[83],"representation":[86],"space.":[87],"To":[88],"assemble":[89],"outputs,":[92],"attention":[96,121],"module":[97],"generate":[99],"connections":[100],"between":[101],"achieve":[106],"best":[108],"automatically.":[110],"proposed":[112,134],"can":[114],"effectively":[115],"task":[117],"relationships":[118],"soft":[120],"weights":[122],"alleviate":[124],"mutual":[125],"interference":[126],"through":[127],"independent":[128],"networks.":[130],"We":[131],"use":[132],"improve":[137],"both":[138],"sample":[139],"efficiency":[140],"overall":[142],"over":[144],"baseline":[145],"algorithms":[146],"Meta-world,":[148],"benchmark":[150],"containing":[155],"50":[156],"robotic":[157],"manipulation":[158],"MUJOCO":[163],"environment,":[164],"contains":[166],"four":[167],"considerably":[168],"with":[171],"diverse":[172],"state":[173],"transition":[174],"dynamics.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}