{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T15:52:29Z","timestamp":1782402749862,"version":"3.54.5"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"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":["62206151"],"award-info":[{"award-number":["62206151"]}],"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":["62088102"],"award-info":[{"award-number":["62088102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China National Postdoctoral Program for Innovative Talents","award":["BX20220167"],"award-info":[{"award-number":["BX20220167"]}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20230484362"],"award-info":[{"award-number":["20230484362"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shuimu Tsinghua Scholar Program"},{"name":"Natural Science Foundation of Fujian Province of China","award":["2022J01656"],"award-info":[{"award-number":["2022J01656"]}]},{"name":"U.K. Royal Society Newton Advanced Fellowship","award":["NAF-R1-191082"],"award-info":[{"award-number":["NAF-R1-191082"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tpami.2024.3511936","type":"journal-article","created":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T18:55:44Z","timestamp":1733770544000},"page":"1975-1990","source":"Crossref","is-referenced-by-count":7,"title":["Spiking Variational Policy Gradient for Brain Inspired Reinforcement Learning"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7908-9524","authenticated-orcid":false,"given":"Zhile","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science, University of Leeds, Leeds, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3181-6881","authenticated-orcid":false,"given":"Shangqi","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Precision Instrument, Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Fang","sequence":"additional","affiliation":[{"name":"College of Computer and Cyber Security, Fujian Normal University, Fujian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6913-7553","authenticated-orcid":false,"given":"Zhaofei","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5391-7213","authenticated-orcid":false,"given":"Jian K.","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Leeds, Leeds, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2994002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2939-8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3192418"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref6","first-page":"1","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nagabandi"},{"key":"ref7","first-page":"7968","article-title":"Improving generalization in reinforcement learning with mixture regularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref8","first-page":"6215","article-title":"Action robust reinforcement learning and applications in continuous control","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Tessler"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3356981"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2019.00260"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2020.2968588"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adc8892"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3114196"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abn0984"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.08.009"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-17236-y"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3407197.3407221"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3389\/fncir.2015.00085"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01238"},{"key":"ref20","article-title":"Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets","author":"Bellec","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.09.036"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25891-6_42"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460482"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2018.00774"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.11.107"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793774"},{"key":"ref27","first-page":"136","article-title":"Variational learning for recurrent spiking networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Rezende"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2768554"},{"key":"ref29","first-page":"4597","article-title":"VOWEL: A local online learning rule for recurrent networks of probabilistic spiking winner-take-all circuits","volume-title":"Proc. Int. Conf. Pattern Recognit.","author":"Jang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2871144"},{"key":"ref31","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref32","article-title":"The MNIST Database of Handwritten Digits","author":"LeCun","year":"1998"},{"key":"ref33","article-title":"OpenAI gym","author":"Brockman","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tg.2018.2877047"},{"key":"ref35","article-title":"AI2-THOR: An interactive 3D environment for visual AI","author":"Kolve","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00323"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref38","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref39","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref40","first-page":"1","article-title":"Overview of mini-batch gradient descent","volume":"575","author":"Hinton","year":"2012","journal-title":"Neural Netw. Mach. Learn."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/app10249013"},{"key":"ref43","article-title":"Biologically plausible variational policy gradient with spiking recurrent winner-take-all networks","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Yang"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1003037"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1003024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2007.19.6.1468"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2526029"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107447615"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1038\/35092560"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1038\/35000586"},{"key":"ref51","article-title":"Reinforcement learning with feedback-modulated TD-STDP","author":"Chung","year":"2020"},{"key":"ref52","first-page":"43","article-title":"Actor-critic reinforcement learning with energy-based policies","volume-title":"Proc. Eur. Workshop Reinforcement Learn.","author":"Heess"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1561\/2200000001"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref55","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref57","article-title":"PyRep: Bringing V-REP to deep robot learning","author":"James","year":"2019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/BRACIS.2019.00079"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-49724-8_10"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2017.00682"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adi1480"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01086"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2023.3308088"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.05.015"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2019.00625"},{"key":"ref67","first-page":"1","article-title":"Reinforcement learning with a network of spiking agents","author":"Aenugu"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851732"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TNANO.2018.2821131"},{"key":"ref70","article-title":"State and action abstraction in reinforcement learning","author":"Guo","year":"2021"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3198259"},{"key":"ref72","first-page":"2016","article-title":"Deep reinforcement learning with population-coded spiking neural network for continuous control","volume-title":"Proc. Conf. Robot Learn.","author":"Tang"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340948"},{"key":"ref74","article-title":"Deep reinforcement learning with spiking Q-learning","author":"Chen","year":"2022"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10873290\/10786920.pdf?arnumber=10786920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T06:00:06Z","timestamp":1738821606000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10786920\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":74,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3511936","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}