{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T23:57:43Z","timestamp":1768348663550,"version":"3.49.0"},"reference-count":25,"publisher":"IEEE","funder":[{"DOI":"10.13039\/501100001729","name":"Swedish Foundation for Strategic Research","doi-asserted-by":"publisher","award":["RIT17-0046"],"award-info":[{"award-number":["RIT17-0046"]}],"id":[{"id":"10.13039\/501100001729","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,25]]},"DOI":"10.23919\/acc50511.2021.9483025","type":"proceedings-article","created":{"date-parts":[[2021,7,28]],"date-time":"2021-07-28T20:29:16Z","timestamp":1627504156000},"page":"4561-4567","source":"Crossref","is-referenced-by-count":13,"title":["Towards Optimal Attacks on Reinforcement Learning Policies"],"prefix":"10.23919","author":[{"given":"Alessio","family":"Russo","sequence":"first","affiliation":[]},{"given":"Alexandre","family":"Proutiere","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref11","article-title":"Deep recurrent q-learning for partially observable mdps","author":"hausknecht","year":"2015","journal-title":"2015 AAAI Fall Symposium Series"},{"key":"ref12","article-title":"Robust deep reinforcement learning against adversarial perturbations on observations","author":"zhang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref13","article-title":"Optimal attacks on reinforcement learning policies","author":"russo","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-62416-7_19"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/525"},{"key":"ref16","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"4577","DOI":"10.1609\/aaai.v34i04.5887","article-title":"Spa-tiotemporally constrained action space attacks on deep reinforcement learning agents","volume":"34","author":"lee","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053011528"},{"key":"ref19","article-title":"Robust adversarial reinforcement learning","volume":"70","author":"pinto","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"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":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref6","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref5","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref8","article-title":"Adversarial attacks on neural network policies","author":"huang","year":"2017","journal-title":"Workshop Track of the 5th International Conference on Learning Representations Toulon France"},{"key":"ref7","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":"ref2","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref9","first-page":"2040","article-title":"Robust deep reinforcement learning with adversarial attacks","author":"pattanaik","year":"2018","journal-title":"Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems International Foundation for Autonomous Agents and Multiagent Systems"},{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"NIPS Deep Learning Workshop"},{"key":"ref20","article-title":"Delving into adversarial attacks on deep policies","author":"kos","year":"2017","journal-title":"International Conference on Learning Representations Workshops Track"},{"key":"ref22","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"ICML"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50042-8"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1016\/0022-247X(65)90154-X","article-title":"Optimal control of markov processes with incomplete state information","volume":"10","author":"astrom","year":"1965","journal-title":"Journal of Mathematical Analysis and Applications"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_12"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"}],"event":{"name":"2021 American Control Conference (ACC)","location":"New Orleans, LA, USA","start":{"date-parts":[[2021,5,25]]},"end":{"date-parts":[[2021,5,28]]}},"container-title":["2021 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9482409\/9482614\/09483025.pdf?arnumber=9483025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,6]],"date-time":"2021-10-06T10:51:01Z","timestamp":1633517461000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9483025\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,25]]},"references-count":25,"URL":"https:\/\/doi.org\/10.23919\/acc50511.2021.9483025","relation":{},"subject":[],"published":{"date-parts":[[2021,5,25]]}}}