{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:12:36Z","timestamp":1774627956323,"version":"3.50.1"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"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":[[2023,9]]},"DOI":"10.1109\/tnnls.2021.3129525","type":"journal-article","created":{"date-parts":[[2021,12,7]],"date-time":"2021-12-07T20:31:30Z","timestamp":1638909090000},"page":"6656-6662","source":"Crossref","is-referenced-by-count":5,"title":["QC_SANE: Robust Control in DRL Using Quantile Critic With Spiking Actor and Normalized Ensemble"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8356-1836","authenticated-orcid":false,"given":"Surbhi","family":"Gupta","sequence":"first","affiliation":[{"name":"Department of Computer Science Engineering, Bennett University, Greater Noida, Uttar Pradesh, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7570-6292","authenticated-orcid":false,"given":"Gaurav","family":"Singal","sequence":"additional","affiliation":[{"name":"Department of Computer Science Engineering, Netaji Subhas University of Technology, New Delhi, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deepak","family":"Garg","sequence":"additional","affiliation":[{"name":"Department of Computer Science Engineering, Bennett University, Greater Noida, Uttar Pradesh, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2310-3737","authenticated-orcid":false,"given":"Sarangapani","family":"Jagannathan","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"5556","article-title":"Controlling overestimation bias with truncated mixture of continuous distributional quantile critics","author":"kuznetsov","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","article-title":"Single-model uncertainties for deep learning","author":"tagasovska","year":"2018","journal-title":"arXiv 1811 00908"},{"key":"ref15","article-title":"SEERL: Sample efficient ensemble reinforcement learning","author":"saphal","year":"2020","journal-title":"arXiv 2001 05209"},{"key":"ref14","article-title":"Beyond pinball loss: Quantile methods for calibrated uncertainty quantification","author":"chung","year":"2020","journal-title":"arXiv 2011 09588"},{"key":"ref30","article-title":"Addressing variance shrinkage in variational autoencoders using quantile regression","author":"akrami","year":"2020","journal-title":"arXiv 2010 09042"},{"key":"ref11","article-title":"Self-normalizing neural networks","author":"klambauer","year":"2017","journal-title":"arXiv 1706 02515"},{"key":"ref10","article-title":"Deep reinforcement learning with population-coded spiking neural network for continuous control","author":"tang","year":"2020","journal-title":"arXiv 2010 09635"},{"key":"ref2","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref17","article-title":"Learning to run with actor-critic ensemble","author":"huang","year":"2017","journal-title":"arXiv 1712 08987"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015789"},{"key":"ref19","author":"hill","year":"2018","journal-title":"Stable Baselines"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref24","article-title":"Enabling deep spiking neural networks with hybrid conversion and spike timing dependent backpropagation","author":"rathi","year":"2020","journal-title":"arXiv 2005 01807"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3034067"},{"key":"ref26","author":"takeuchi","year":"2006","journal-title":"Nonparametric Quantile Estimation"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(97)00011-7"},{"key":"ref20","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"arXiv 1801 01290"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053856"},{"key":"ref21","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2010.66"},{"key":"ref27","article-title":"Learning policies through quantile regression","author":"richter","year":"2019","journal-title":"arXiv 1906 11941"},{"key":"ref29","article-title":"AC-Teach: A Bayesian actor-critic method for policy learning with an ensemble of suboptimal teachers","author":"kurenkov","year":"2019","journal-title":"arXiv 1909 04121"},{"key":"ref8","first-page":"7424","article-title":"Can increasing input dimensionality improve deep reinforcement learning?","author":"ota","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","first-page":"1","article-title":"DSAC: Distributional soft actor critic for risk-sensitive reinforcement learning","author":"ma","year":"2020","journal-title":"Proc Reinforcement Learn Real Life Workshop ICML"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.08.009"},{"key":"ref4","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-021-09552-3"},{"key":"ref5","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10237282\/09640528.pdf?arnumber=9640528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:28:53Z","timestamp":1695666533000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9640528\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":30,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3129525","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}