{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T18:35:28Z","timestamp":1782412528800,"version":"3.54.5"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"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":["61976215"],"award-info":[{"award-number":["61976215"]}],"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":["61772532"],"award-info":[{"award-number":["61772532"]}],"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":["61751202"],"award-info":[{"award-number":["61751202"]}],"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":["U1813203"],"award-info":[{"award-number":["U1813203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1109\/tcds.2020.3034452","type":"journal-article","created":{"date-parts":[[2020,10,28]],"date-time":"2020-10-28T19:58:01Z","timestamp":1603915081000},"page":"1023-1032","source":"Crossref","is-referenced-by-count":17,"title":["Off-Policy Deep Reinforcement Learning Based on Steffensen Value Iteration"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2022-9999","authenticated-orcid":false,"given":"Yuhu","family":"Cheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-7230","authenticated-orcid":false,"given":"C. L. Philip","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-1088","authenticated-orcid":false,"given":"Xuesong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1111\/ecog.00888"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2005.1494750"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10255-017-0648-3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/0705026"},{"key":"ref36","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref10","first-page":"2939","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","first-page":"449","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927227"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2806087"},{"key":"ref14","author":"lillicrap","year":"2019","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref15","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref17","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref18","author":"zoph","year":"2016","journal-title":"Neural architecture search with reinforcement learning"},{"key":"ref19","first-page":"2852","article-title":"SeqGAN: Sequence generative adversarial nets with policy gradient","author":"yu","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1090.0705"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017928328829"},{"key":"ref27","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref6","author":"devlin","year":"2019","journal-title":"BERT Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref29","author":"goyal","year":"2020","journal-title":"A first-order approach to accelerated value iteration"},{"key":"ref5","article-title":"Deep convolutional network based on interleaved fusion group","author":"lv","year":"2020","journal-title":"IEEE Trans Cogn Develop Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref9","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","author":"jiang","year":"2017","journal-title":"A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2628817"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2718938"},{"key":"ref24","first-page":"1407","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","author":"espeholt","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2649564"},{"key":"ref26","author":"schaul","year":"2016","journal-title":"Prioritized experience replay"},{"key":"ref25","author":"barth-maron","year":"2018","journal-title":"Distributed Distributional Deterministic Policy Gradients"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/9645278\/09241824.pdf?arnumber=9241824","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:25Z","timestamp":1652194465000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9241824\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":36,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2020.3034452","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12]]}}}