{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T13:16:40Z","timestamp":1752671800606,"version":"3.37.3"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Grant-in-Aid for Scientific Research on Innovative Areas, JSPS KAKENHI, Japan","doi-asserted-by":"publisher","award":["JP17H06310"],"award-info":[{"award-number":["JP17H06310"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Grant-in-Aid for Scientific Research B, JSPS KAKENHI, Japan","doi-asserted-by":"publisher","award":["JP19H04180"],"award-info":[{"award-number":["JP19H04180"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001863","name":"New Energy and Industrial Technology Development Organization (NEDO), Japan","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001863","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3121751","type":"journal-article","created":{"date-parts":[[2021,10,27]],"date-time":"2021-10-27T19:57:46Z","timestamp":1635364666000},"page":"143901-143912","source":"Crossref","is-referenced-by-count":6,"title":["Deep Adversarial Reinforcement Learning With Noise Compensation by Autoencoder"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9116-0952","authenticated-orcid":false,"given":"Kohei","family":"Ohashi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0078-6942","authenticated-orcid":false,"given":"Kosuke","family":"Nakanishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wataru","family":"Sasaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuji","family":"Yasui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9385-8230","authenticated-orcid":false,"given":"Shin","family":"Ishii","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Deep Learning","year":"2016","author":"goodfellow","key":"ref39"},{"key":"ref38","first-page":"1","article-title":"Robust deep reinforcement learning with adversarial attacks","volume":"3","author":"pattanaik","year":"2018","journal-title":"Proc Int Joint Conf Auton Agents Multiagent Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206245"},{"key":"ref32","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053011528"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2886017"},{"key":"ref37","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","author":"zhang","year":"2020","journal-title":"arXiv 2003 08938"},{"key":"ref36","first-page":"1","article-title":"Adversarial policies: Attacking deep reinforcement learning","author":"gleave","year":"2019","journal-title":"Int Conf Learn Represent (ICLR)"},{"key":"ref35","first-page":"1328","article-title":"Certified adversarial robustness for deep reinforcement learning","author":"l\u00fctjens","year":"2020","journal-title":"Proc Conf Robot Learn"},{"key":"ref34","article-title":"Characterizing attacks on deep reinforcement learning","author":"xiao","year":"2019","journal-title":"arXiv 1907 09470"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1177\/0278364917710318","article-title":"Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection","volume":"37","author":"levine","year":"2017","journal-title":"Int J Robot Res"},{"key":"ref40","first-page":"4148","article-title":"The arcade learning environment: An evaluation platform for general agents","author":"bellemare","year":"2015","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref11","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3053009"},{"key":"ref13","article-title":"Challenges and countermeasures for adversarial attacks on deep reinforcement learning","author":"ilahi","year":"2020","journal-title":"arXiv 2001 09684"},{"key":"ref14","first-page":"1","article-title":"Loss is its own reward: Self-supervision for reinforcement learning","author":"shelhamer","year":"2017","journal-title":"Proc 5th Int Conf Learn Represent (ICLR)"},{"key":"ref15","first-page":"1","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"2017","journal-title":"Proc 5th Int Conf Learn Represent (ICLR)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"hinton","year":"2006","journal-title":"Science"},{"key":"ref18","first-page":"899","article-title":"Generalized denoising auto-encoders as generative models","author":"bengio","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","first-page":"2059","article-title":"Denoising criterion for variational auto-encoding framework","author":"im","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00090"},{"key":"ref3","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"hasselt","year":"2016","journal-title":"Proc 13th AAAI Conf Artif Intell"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/525"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_9"},{"key":"ref5","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref8","article-title":"Adversarial attacks on neural network policies","author":"huang","year":"2017","journal-title":"arXiv 1702 02284"},{"key":"ref7","first-page":"1","article-title":"Intriguing properties of neural networks","author":"szegedy","year":"2014","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref9","first-page":"468","article-title":"Explaining and harnessing adversarial examples","volume":"33","author":"goodfellow","year":"2014","journal-title":"Int J Ser Solid Mech Strength Mater"},{"key":"ref1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref20","first-page":"2578","article-title":"Adversarial examples: Opportunities and challenges","volume":"31","author":"zhang","year":"2020","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"journal-title":"Waymo Open Dataset","year":"0","key":"ref45"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref21","article-title":"Adversarial examples in the physical world","author":"kurakin","year":"2016","journal-title":"arXiv 1607 02533"},{"key":"ref42","article-title":"Unity: A general platform for intelligent agents","author":"juliani","year":"2018","journal-title":"arXiv 1809 02627"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140444"},{"key":"ref41","first-page":"1","article-title":"Chainer: A next-generation open source framework for deep learning","author":"tokui","year":"2015","journal-title":"Proc 29th Annu Conf Neural Inf Process Syst (NIPS)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref44","first-page":"1","article-title":"Rainbow: Combining improvements in deep reinforcement learning","volume":"abs 1710 2298","author":"hessel","year":"2017","journal-title":"CoRR"},{"key":"ref26","first-page":"2137","article-title":"Black-box adversarial attacks with limited queries and information","volume":"5","author":"eyas","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn (ICML)"},{"key":"ref43","article-title":"Self-driving scale car trained by deep reinforcement learning","author":"zhang","year":"2019","journal-title":"arXiv 1909 03467"},{"key":"ref25","first-page":"1","article-title":"Adversarial machine learning at scale","author":"kurakin","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09583275.pdf?arnumber=9583275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,21]],"date-time":"2022-02-21T22:17:49Z","timestamp":1645481869000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9583275\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3121751","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}