{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T03:27:16Z","timestamp":1769743636522,"version":"3.49.0"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000646","name":"Grant-in-Aid for Scientific Research S from Japanese Society for the Promotion of Science KAKENHI, Japan","doi-asserted-by":"publisher","award":["22H04998"],"award-info":[{"award-number":["22H04998"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001863","name":"New Energy and Industrial Technology Development Organization (NEDO), Japan","doi-asserted-by":"publisher","award":["22H04998"],"award-info":[{"award-number":["22H04998"]}],"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":[[2024]]},"DOI":"10.1109\/access.2024.3479089","type":"journal-article","created":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T17:25:51Z","timestamp":1728926751000},"page":"151907-151919","source":"Crossref","is-referenced-by-count":2,"title":["Orthogonal Adversarial Deep Reinforcement Learning for Discrete- and Continuous-Action Problems"],"prefix":"10.1109","volume":"12","author":[{"given":"Kohei","family":"Ohashi","sequence":"first","affiliation":[{"name":"Department of Systems Science, Graduate School of Informatics, Kyoto University, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0078-6942","authenticated-orcid":false,"given":"Kosuke","family":"Nakanishi","sequence":"additional","affiliation":[{"name":"Department of Systems Science, Graduate School of Informatics, Kyoto University, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nao","family":"Goto","sequence":"additional","affiliation":[{"name":"Department of Systems Science, Graduate School of Informatics, Kyoto University, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuji","family":"Yasui","sequence":"additional","affiliation":[{"name":"Honda Research and Development Innovative Research Center, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9385-8230","authenticated-orcid":false,"given":"Shin","family":"Ishii","sequence":"additional","affiliation":[{"name":"Department of Systems Science, Graduate School of Informatics, Kyoto University, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky"},{"key":"ref2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"issue":"4","key":"ref5","first-page":"468","article-title":"Explaining and harnessing adversarial examples","volume":"33","author":"Goodfellow","year":"2014","journal-title":"Int. J. Solid Mech., Strength Mater."},{"key":"ref6","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013","journal-title":"arXiv:1312.6199"},{"key":"ref7","article-title":"Adversarial attacks on neural network policies","author":"Huang","year":"2017","journal-title":"arXiv:1702.02284"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140444"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3053009"},{"issue":"1","key":"ref13","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21918"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3111139"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053011528"},{"key":"ref18","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","volume":"70","author":"Pinto"},{"key":"ref19","first-page":"1","article-title":"Robust deep reinforcement learning with adversarial attacks","volume-title":"Proc. Int. Joint Conf. Auto. Agents Multiagent Syst. (AAMAS)","volume":"3","author":"Pattanaik"},{"key":"ref20","article-title":"Adversarial policies: Attacking deep reinforcement learning","author":"Gleave","year":"2019","journal-title":"arXiv:1905.10615"},{"key":"ref21","first-page":"1328","article-title":"Certified adversarial robustness for deep reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"L\u00fctjens"},{"key":"ref22","first-page":"21024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zhang"},{"key":"ref23","article-title":"Robust reinforcement learning on state observations with learned optimal adversary","author":"Zhang","year":"2021","journal-title":"arXiv:2101.08452"},{"key":"ref24","first-page":"22547","article-title":"Efficient adversarial training without attacking: Worst-case-aware robust reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Liang"},{"key":"ref25","article-title":"Who is the strongest enemy? Towards optimal and efficient evasion attacks in deep RL","author":"Sun","year":"2021","journal-title":"arXiv:2106.05087"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3121751"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3314750"},{"key":"ref28","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref29","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Haarnoja"},{"key":"ref30","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206245"},{"key":"ref33","first-page":"1010","article-title":"Characterizing attacks on deep reinforcement learning","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst. (AAMAS)","author":"Pan"},{"key":"ref34","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proc. 19th Int. Conf. Mach. Learn.","author":"Kakade"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref37","article-title":"Lecture 6.5\u2014rmsprop: Divide the gradient by a running average of its recent magnitude","author":"Tieleman","year":"2012","journal-title":"COURSERA, Neural Netw. Mach. Learn."},{"key":"ref38","first-page":"1","article-title":"Chainer: A next-generation open source framework for deep learning","volume-title":"Proc. 29th Workshop Mach. Learn. Syst. Neural Inf. Process. Syst. (NIPS)","volume":"5","author":"Tokui"},{"key":"ref39","volume-title":"Pybullet, a Python Module for Physics Simulation for Games, Robotics and Machine Learning","author":"Coumans","year":"2016"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10716555.pdf?arnumber=10716555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:53:57Z","timestamp":1732668837000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10716555\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3479089","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}