{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:41:38Z","timestamp":1770918098099,"version":"3.50.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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\/501100001809","name":"Shenzhen Fundamental Research","doi-asserted-by":"publisher","award":["JCYJ20220818102415033"],"award-info":[{"award-number":["JCYJ20220818102415033"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Shenzhen Fundamental Research","doi-asserted-by":"publisher","award":["JSGG20201103093802006"],"award-info":[{"award-number":["JSGG20201103093802006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Shenzhen Fundamental Research","doi-asserted-by":"publisher","award":["KJZD20230923114222045"],"award-info":[{"award-number":["KJZD20230923114222045"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tnnls.2024.3386225","type":"journal-article","created":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T14:01:09Z","timestamp":1714140069000},"page":"6556-6568","source":"Crossref","is-referenced-by-count":7,"title":["Distributional Policy Gradient With Distributional Value Function"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7485-6344","authenticated-orcid":false,"given":"Qi","family":"Liu","sequence":"first","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, 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":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9887-590X","authenticated-orcid":false,"given":"Xiongtao","family":"Shi","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, 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":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, 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":"Huawei Noah’s Ark Lab, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8203-7795","authenticated-orcid":false,"given":"Yunjiang","family":"Lou","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and the School of Mechanical Engineering and Automation, 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\/TPAMI.2019.2956703"},{"key":"ref3","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lillicrap"},{"key":"ref4","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3054402"},{"key":"ref6","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3089493"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref9","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Int. Conf. Mach. Learn.","volume":"48","author":"Wang"},{"key":"ref10","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref11","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bellemare"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1924-6"},{"key":"ref13","volume-title":"Distributional Reinforcement Learning","author":"Bellemare","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref15","article-title":"Distributed distributional deterministic policy gradients","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Barth-Maron"},{"key":"ref16","first-page":"1","article-title":"Fully parameterized quantile function for distributional reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref18","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dabney"},{"key":"ref19","first-page":"5528","article-title":"Statistics and samples in distributional reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rowland"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1257\/jep.15.4.143"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref22","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/84537.84552"},{"key":"ref24","first-page":"1","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Sutton"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref26","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref28","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref29","article-title":"Data-efficient deep reinforcement learning for dexterous manipulation","author":"Popov","year":"2017","journal-title":"arXiv:1704.03073"},{"key":"ref30","article-title":"Distributed prioritized experience replay","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Horgan"},{"key":"ref31","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref32","article-title":"Prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Schaul"},{"key":"ref33","article-title":"Distributional policy optimization: An alternative approach for continuous control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Tessler"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3082568"},{"key":"ref35","article-title":"DSAC-T: Distributional soft actor-critic with three refinements","author":"Duan","year":"2023","journal-title":"arXiv:2310.05858"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25864"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2959129"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3089425"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3212273"},{"key":"ref40","article-title":"On-policy policy gradient reinforcement learning without on-policy sampling","author":"Corrado","year":"2023","journal-title":"arXiv:2311.08290"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.2307\/1428011"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176345637"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10949581\/10508809.pdf?arnumber=10508809","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:11Z","timestamp":1764959951000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10508809\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":43,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3386225","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}