{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,29]],"date-time":"2026-03-29T06:59:47Z","timestamp":1774767587994,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61977019"],"award-info":[{"award-number":["61977019"]}],"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":["U1813206"],"award-info":[{"award-number":["U1813206"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017607","name":"Shenzhen Municipal Fundamental Research Program","doi-asserted-by":"publisher","award":["JCYJ20180507183837726"],"award-info":[{"award-number":["JCYJ20180507183837726"]}],"id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017607","name":"Shenzhen Municipal Fundamental Research Program","doi-asserted-by":"publisher","award":["JCYJ20220818102415033"],"award-info":[{"award-number":["JCYJ20220818102415033"]}],"id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017607","name":"Shenzhen Municipal Fundamental Research Program","doi-asserted-by":"publisher","award":["JSGG20201103093802006"],"award-info":[{"award-number":["JSGG20201103093802006"]}],"id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tetci.2024.3369641","type":"journal-article","created":{"date-parts":[[2024,3,11]],"date-time":"2024-03-11T14:22:59Z","timestamp":1710166979000},"page":"2949-2961","source":"Crossref","is-referenced-by-count":7,"title":["Data Efficient Deep Reinforcement Learning With Action-Ranked Temporal Difference Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7485-6344","authenticated-orcid":false,"given":"Qi","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7890-9677","authenticated-orcid":false,"given":"Yanjie","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3683-7959","authenticated-orcid":false,"given":"Yuecheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3429-5877","authenticated-orcid":false,"given":"Ke","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4486-3740","authenticated-orcid":false,"given":"Jianqi","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8203-7795","authenticated-orcid":false,"given":"Yunjiang","family":"Lou","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, Harbin Institute of Technology, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3166555"},{"key":"ref3","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","year":"2018"},{"key":"ref4","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3083410"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref8","article-title":"Prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schaul","year":"2016"},{"key":"ref9","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref11","article-title":"Noisy networks for exploration","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fortunato","year":"2017"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/14207.001.0001","article-title":"Distributional Reinforcement Learning.","author":"Bellemare","year":"2023"},{"key":"ref13","volume-title":"Reinforcement Learning: An Introduction.","author":"Sutton","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref15","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Auton. Agents Multiagent Syst.","author":"Sunehag","year":"2018"},{"key":"ref16","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref17","article-title":"Rethinking the implementation tricks and monotonicity constraint in cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations Blogposts","author":"Hu","year":"2023"},{"key":"ref18","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref19","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schulman","year":"2016"},{"key":"ref20","first-page":"3667","article-title":"Control variates for slate off-policy evaluation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vlassis","year":"2021"},{"key":"ref21","article-title":"A review of off-policy evaluation in reinforcement learning","author":"Uehara","year":"2022"},{"key":"ref22","first-page":"2613","article-title":"Double Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hasselt","year":"2010"},{"key":"ref23","first-page":"213","article-title":"R-max-a general polynomial time algorithm for near-optimal reinforcement learning","volume":"3","author":"Brafman","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref24","first-page":"2750","article-title":"#Exploration: A study of count-based exploration for deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tang","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119217"},{"key":"ref27","article-title":"Exploration in deep reinforcement learning: A comprehensive survey","author":"Yang","year":"2021"},{"key":"ref28","article-title":"Data-efficient reinforcement learning with self-predictive representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schwarzer","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"key":"ref30","first-page":"25476","article-title":"Mastering atari games with limited data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ye","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2009.V.026"},{"key":"ref32","article-title":"A survey of learning in multiagent environments: Dealing with non-stationarity","author":"Hernandez-Leal","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"key":"ref34","first-page":"189","article-title":"Evolutionsstrategie: Optimierung technischer systeme nach prinzipien der biologischen evolution. frommann-holzbog, stuttgart, 1973, Step-size adaptation based on non-local use of selection information","volume-title":"Proc. Int. Conf. Parallel Problem Solving Nature","author":"Rechenberg","year":"1994"},{"key":"ref35","first-page":"2186","article-title":"The StarCraft multi-agent challenge","volume-title":"Proc. Int. Joint Conf. Auton. Agents Multiagent Syst.","author":"Whiteson","year":"2019"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7433297\/10607834\/10466624.pdf?arnumber=10466624","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T20:51:15Z","timestamp":1772225475000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10466624\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":35,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2024.3369641","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}