{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:51:31Z","timestamp":1775065891723,"version":"3.50.1"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2021ZD0112700"],"award-info":[{"award-number":["2021ZD0112700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61921004"],"award-info":[{"award-number":["61921004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62236002"],"award-info":[{"award-number":["62236002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62173251"],"award-info":[{"award-number":["62173251"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhishan” Scholars Programs of Southeast University"},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/lra.2023.3271445","type":"journal-article","created":{"date-parts":[[2023,5,12]],"date-time":"2023-05-12T17:46:26Z","timestamp":1683913586000},"page":"3812-3819","source":"Crossref","is-referenced-by-count":26,"title":["Multi-Task Reinforcement Learning With Attention-Based Mixture of Experts"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0865-532X","authenticated-orcid":false,"given":"Guangran","family":"Cheng","sequence":"first","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6737-1381","authenticated-orcid":false,"given":"Lu","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4610-3454","authenticated-orcid":false,"given":"Wenzhe","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9269-334X","authenticated-orcid":false,"given":"Changyin","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981244"},{"key":"ref12","first-page":"4499","article-title":"Distral: Robust multitask reinforcement learning","author":"teh","year":"0","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref15","first-page":"3511","article-title":"Pseudo-task augmentation: From deep multitask learning to intratask sharing—and back","author":"meyerson","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205489"},{"key":"ref31","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"liu","year":"2019"},{"key":"ref30","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref11","first-page":"1","article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","author":"parisotto","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref10","first-page":"4767","article-title":"Multi-task reinforcement learning with soft modularization","author":"yang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","first-page":"1","article-title":"Model based reinforcement learning for atari","author":"kaiser","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref2","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref17","first-page":"3854","article-title":"Learning to branch for multi-task learning","author":"guo","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","first-page":"8728","article-title":"AdaShare: Learning what to share for efficient deep multi-task learning","author":"sun","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","first-page":"9767","article-title":"Multi-task reinforcement learning with context-based representations","author":"sodhani","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-46133-1_9"},{"key":"ref24","first-page":"1","article-title":"Sharing knowledge in multi-task deep reinforcement learning","author":"d'eramo","year":"0","journal-title":"Proc 8th Int Conf Learn Representations"},{"key":"ref23","first-page":"18878","article-title":"Conflict-averse gradient descent for multi-task learning","author":"liu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref25","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","author":"yu","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref20","article-title":"Regularizing deep multi-task networks using orthogonal gradients","author":"suteu","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013796"},{"key":"ref21","article-title":"Adapting auxiliary losses using gradient similarity","author":"du","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412236"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.181"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3184805"},{"key":"ref9","first-page":"5824","article-title":"Gradient surgery for multi-task learning","author":"yu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196132"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10102643\/10111062.pdf?arnumber=10111062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T18:41:34Z","timestamp":1723056094000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10111062\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":32,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3271445","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}