{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T18:45:59Z","timestamp":1757616359823,"version":"3.44.0"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tnnls.2025.3564078","type":"journal-article","created":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T14:01:20Z","timestamp":1746799280000},"page":"16854-16863","source":"Crossref","is-referenced-by-count":0,"title":["Multistate Temporal Difference Target for Model-Free Reinforcement Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5343-5951","authenticated-orcid":false,"given":"Wuhao","family":"Wang","sequence":"first","affiliation":[{"name":"School of Engineering, The University of Newcastle, Callaghan, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2033-4249","authenticated-orcid":false,"given":"Zhiyong","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Engineering, The University of Newcastle, Callaghan, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5319-2996","authenticated-orcid":false,"given":"Lepeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science, Linköping University, Linköping, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2022.3229054"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2018.2830357"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111687"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120112"},{"key":"ref6","first-page":"255","article-title":"Issues in using function approximation for reinforcement learning","volume-title":"Proceedings of the 1993 Connectionist Models Summer School","author":"Thrun"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.7554\/elife.20944.012"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Represent.","author":"Lillicrap","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3387168.3387199"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. 4th Int. Conf. Learn. Represent.","author":"Schulman","key":"ref12"},{"key":"ref13","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11631"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-019-01417-4"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413027"},{"key":"ref19","article-title":"Model-based value estimation for efficient model-free reinforcement learning","author":"Feinberg","year":"2018","journal-title":"arXiv:1803.00101"},{"key":"ref20","first-page":"8234","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Buckman"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3233\/faia230427"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013598"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3262751"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2019.113755"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICACI58115.2023.10146186"},{"key":"ref26","article-title":"An improved strategy for blood glucose control using multi-step deep reinforcement learning","author":"Gu","year":"2024","journal-title":"arXiv:2403.07566"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICHI.2017.45"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.05.011"},{"volume-title":"Gymnasium","year":"2023","author":"Towers","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1201\/9781003143444"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1185"},{"key":"ref33","first-page":"1","article-title":"Convergence of Q-learning: A simple proof","author":"Melo","year":"2001"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11151745\/10993338.pdf?arnumber=10993338","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T18:24:15Z","timestamp":1757096655000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10993338\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":33,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3564078","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}