{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T09:32:48Z","timestamp":1781343168231,"version":"3.54.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Science and Technology Innovation Committee Foundation of Shenzhen","award":["JCYJ20200109143223052"],"award-info":[{"award-number":["JCYJ20200109143223052"]}]},{"name":"Hong Kong Research Grant Council","award":["11218621"],"award-info":[{"award-number":["11218621"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tetci.2024.3359039","type":"journal-article","created":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T19:24:46Z","timestamp":1707247486000},"page":"1865-1881","source":"Crossref","is-referenced-by-count":10,"title":["Time-Varying Weights in Multi-Reward Architecture for Deep Reinforcement Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4857-5439","authenticated-orcid":false,"given":"Meng","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8563-148X","authenticated-orcid":false,"given":"Xinhong","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6951-2392","authenticated-orcid":false,"given":"Yechao","family":"She","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5337-487X","authenticated-orcid":false,"given":"Yang","family":"Jin","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9318-1482","authenticated-orcid":false,"given":"Jianping","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1519","article-title":"Distributional reinforcement learning for multi-dimensional reward functions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2021"},{"key":"ref2","first-page":"11298","article-title":"Rd$^{2}$: Reward decomposition with representation decomposition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin","year":"2020"},{"key":"ref3","first-page":"1","article-title":"Hybrid reward architecture for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Seijen","year":"2017"},{"key":"ref4","first-page":"761","article-title":"HORDE: A scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction","volume-title":"Proc. 10th Int. Conf. Auton. Agents Multiagent Syst.","author":"Sutton","year":"2011"},{"key":"ref5","first-page":"1312","article-title":"Universal value function approximators","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schaul","year":"2015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/1643031.1643043"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2020.0443"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s13177-022-00305-5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CAC51589.2020.9327414"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2017.8329799"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2018.8761044"},{"key":"ref12","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref13","article-title":"Reinforcement learning through asynchronous advantage actor--critic on a GPU","author":"Babaeizadeh","year":"2016"},{"key":"ref14","first-page":"2171","article-title":"Scalable Bayesian optimization using deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Snoek","year":"2015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2009.4982974"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956703"},{"key":"ref17","first-page":"10158","article-title":"Tuning-free plug-and-play proximal algorithm for inverse imaging problems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wei","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109448"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.064"},{"key":"ref20","first-page":"1407","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Espeholt","year":"2018"},{"key":"ref21","article-title":"Deep reinforcement learning: An overview","author":"Li","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3579829"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917304"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490437"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2021.3115980"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223407"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.12.001"},{"key":"ref29","first-page":"11","article-title":"Dynamic weights in multi-objective deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Abels","year":"2019"},{"key":"ref30","first-page":"11298","article-title":"RD2: Reward decomposition with representation disentanglement","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Lin","year":"2020"},{"key":"ref31","article-title":"Reinforcement learning by truncating temporal differences","author":"Cichosz","year":"1998"},{"key":"ref32","article-title":"Off-policy correction for actor--critic methods without importance sampling","author":"Saglam","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref34","article-title":"Combining policy gradient and q-learning","author":"ODonoghue","year":"2016"},{"key":"ref35","first-page":"29","article-title":"Deep recurrent Q-learning for partially observable MDPS","volume-title":"Proc. 2015 AAAI Fall Symp. Ser.","author":"Hausknecht","year":"2015"},{"key":"ref36","article-title":"Deep reinforcement learning for real autonomous mobile robot navigation in indoor environments","author":"Surmann","year":"2020"},{"key":"ref37","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR53236.2021.9659344"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197262"},{"key":"ref40","first-page":"1","article-title":"Hindsight experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Andrychowicz","year":"2017"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7433297\/10480102\/10423372.pdf?arnumber=10423372","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T18:56:38Z","timestamp":1732647398000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10423372\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":40,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2024.3359039","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}