{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T20:33:27Z","timestamp":1791491607247,"version":"4.3.4"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197351","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T17:25:46Z","timestamp":1600190746000},"page":"108-114","source":"Crossref","is-referenced-by-count":42,"title":["Training Adversarial Agents to Exploit Weaknesses in Deep Control Policies"],"prefix":"10.1109","author":[{"given":"Sampo","family":"Kuutti","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saber","family":"Fallah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard","family":"Bowden","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Convolutional deep belief networks on cifar-10","volume":"40","author":"krizhevsky","year":"2010","journal-title":"Unpublished manuscript"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref33","first-page":"5014","article-title":"Adversarially robust generalization requires more data","author":"schmidt","year":"2018","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref32","article-title":"Robustness may be at odds with accuracy","author":"tsipras","year":"2018"},{"key":"ref31","article-title":"Training for faster adversarial robustness verification via inducing relu stability","author":"xiao","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917387"},{"key":"ref36","volume":"135","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref35","first-page":"105","article-title":"Incremental natural actor-critic algorithms","author":"bhatnagar","year":"2008","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref34","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref40","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Networks for Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0051"},{"key":"ref12","article-title":"Safely entering the deep: A review of verification and validation for machine learning and a challenge elicitation in the automotive industry","author":"borg","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66284-8_1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.tra.2016.09.010"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-31895-0_17"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MSPEC.2018.8302386"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.4271\/2016-01-0128"},{"key":"ref18","article-title":"Challenges in the verification of reinforcement learning algorithms","author":"van wesel","year":"2017","journal-title":"Technical Report NASA Report"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/538020a"},{"key":"ref28","article-title":"Intriguing properties of neural networks","author":"szegedy","year":"2013"},{"key":"ref4","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500400"},{"key":"ref3","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"ref29","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2962338"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref9","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016"},{"key":"ref1","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref46","article-title":"Reward estimation for variance reduction in deep reinforcement learning","author":"romoff","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2870052"},{"key":"ref45","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053011528"},{"key":"ref47","first-page":"538","article-title":"The optimal reward baseline for gradient-based reinforcement learning","author":"weaver","year":"2001","journal-title":"Proceedings of the Seventeenth Conference on Uncertainty in Artificial Intelligence"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33617-2_17"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/AUV.1992.225178"},{"key":"ref41","article-title":"Carmaker: Virtual testing of automobiles and light-duty vehicles","year":"2017"},{"key":"ref23","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"0"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11694","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref26","article-title":"On a formal model of safe and scalable self-driving cars","author":"shalev-shwartz","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-658-03978-3"},{"key":"ref25","article-title":"Adversarial reinforcement learning framework for benchmarking collision avoidance mechanisms in autonomous vehicles","author":"behzadan","year":"2018"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197351.pdf?arnumber=9197351","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T09:01:37Z","timestamp":1668762097000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197351\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197351","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}