{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T18:10:08Z","timestamp":1747073408169,"version":"3.40.5"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100004335","name":"Southwest University of Science and Technology Ph.D. Fund","doi-asserted-by":"publisher","award":["22zx7164"],"award-info":[{"award-number":["22zx7164"]}],"id":[{"id":"10.13039\/501100004335","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004335","name":"Postgraduate Innovation Fund Project by Southwest University of Science and Technology","doi-asserted-by":"publisher","award":["24ycx2019"],"award-info":[{"award-number":["24ycx2019"]}],"id":[{"id":"10.13039\/501100004335","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2024.3449072","type":"journal-article","created":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T17:58:23Z","timestamp":1724435903000},"page":"80113-80122","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Task Reinforcement Learning Based on Parallel Recombination Networks"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2503-8817","authenticated-orcid":false,"given":"Manlu","family":"Liu","sequence":"first","affiliation":[{"name":"School of Information Engineering, Southwest University of Science and Technology, Mianyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7751-4443","authenticated-orcid":false,"given":"Qingbo","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Southwest University of Science and Technology, Mianyang, China"}]},{"given":"Weimin","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Southwest University of Science and Technology, Mianyang, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7784-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.biortech.2019.121971"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-64987-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/EASCT59475.2023.10392607"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIIP61524.2023.10537686"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICICACS60521.2024.10498636"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2019.8842901"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/01969722.2018.1558013"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-38259-7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3253503"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICICACS60521.2024.10498933"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/AICERA\/ICIS59538.2023.10420185"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref18","article-title":"DiGrad: Multi-task reinforcement learning with shared actions","author":"Dewangan","year":"2018","journal-title":"arXiv:1802.10463"},{"key":"ref19","first-page":"4499","article-title":"Distral: Robust multitask reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Teh"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205489"},{"key":"ref21","first-page":"3511","article-title":"Pseudo-task augmentation: From deep multitask learning to intratask sharing\u2014And back","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Meyerson"},{"key":"ref22","first-page":"8728","article-title":"AdaShare: Learning what to share for efficient deep multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref23","first-page":"3854","article-title":"Learning to branch for multi-task learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo"},{"article-title":"Multi-task reinforcement learning: An hybrid A3C domain approach","volume-title":"Proc. Encontro Nacional de Intell. Artif. Comput.","author":"Birck","key":"ref24"},{"key":"ref25","first-page":"4767","article-title":"Multi-task reinforcement learning with soft modularization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104296"},{"key":"ref27","article-title":"Multi-task reinforcement learning with context-based representations","author":"Sodhani","year":"2021","journal-title":"arXiv:2102.06177"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3271445"},{"key":"ref29","first-page":"5447","article-title":"Policy optimization via importance sampling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Metelli"},{"key":"ref30","first-page":"4572","article-title":"Dimension-wise importance sampling weight clipping for sample-efficient reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Han"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI52525.2021.00199"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.strusafe.2023.102393"},{"key":"ref33","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref34","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref35","first-page":"6740","article-title":"Diverging divergences: Examining variants of Jensen Shannon divergence for corpus comparison tasks","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Lu"},{"key":"ref36","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","author":"Yu","year":"2019","journal-title":"arXiv:1910.10897"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref38","first-page":"1","article-title":"Gradient surgery for multi-task learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref39","first-page":"9767","article-title":"Multi-task reinforcement learning with context-based representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sodhani"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10643964.pdf?arnumber=10643964","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T17:45:25Z","timestamp":1747071925000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10643964\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3449072","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}