{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:52:59Z","timestamp":1776181979920,"version":"3.50.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Singapore under its AI Singapore Programme","doi-asserted-by":"publisher","award":["AISG-RP-2018-004"],"award-info":[{"award-number":["AISG-RP-2018-004"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001475","name":"Data Science and Artificial Intelligence Research Center at Nanyang Technological University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001475","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1109\/tcds.2020.2974509","type":"journal-article","created":{"date-parts":[[2020,2,19]],"date-time":"2020-02-19T22:00:02Z","timestamp":1582149602000},"page":"806-817","source":"Crossref","is-referenced-by-count":31,"title":["Minimalistic Attacks: How Little It Takes to Fool Deep Reinforcement Learning Policies"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8072-2019","authenticated-orcid":false,"given":"Xinghua","family":"Qu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3350-7022","authenticated-orcid":false,"given":"Zhu","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4480-169X","authenticated-orcid":false,"given":"Yew-Soon","family":"Ong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhishek","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2002.800884"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-003-0328-5"},{"key":"ref33","author":"goodfellow","year":"2017","journal-title":"Attacking machine learning with adversarial examples"},{"key":"ref32","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":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref30","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2005.846356"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/sj.jors.2600425"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2890858"},{"key":"ref34","author":"brown","year":"2017","journal-title":"Adversarial Patch"},{"key":"ref10","author":"raghu","year":"2017","journal-title":"Continuous state-space models for optimal sepsis treatment-a deep reinforcement learning approach"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2018.2869001"},{"key":"ref11","first-page":"239","article-title":"Combining kernel and model based learning for HIV therapy selection","volume":"2017","author":"parbhoo","year":"2017","journal-title":"Proc AMIA Summits Transl Sci"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican0792-66"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2009.02.044"},{"key":"ref14","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref15","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","first-page":"5279","article-title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","author":"wu","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","author":"szegedy","year":"2013","journal-title":"Intriguing properties of neural networks"},{"key":"ref18","author":"goodfellow","year":"2014","journal-title":"Explaining and Harnessing Adversarial Examples"},{"key":"ref19","author":"kurakin","year":"2016","journal-title":"Adversarial machine learning at scale"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1287\/moor.12.3.441"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/525"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2932203"},{"key":"ref3","author":"huang","year":"2017","journal-title":"Adversarial attacks on neural network policies"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"key":"ref29","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2886017"},{"key":"ref8","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume":"70","author":"pinto","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref7","first-page":"2040","article-title":"Robust deep reinforcement learning with adversarial attacks","author":"pattanaik","year":"2018","journal-title":"Proc 17th Int Conf Auton Agents MultiAgent Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2694391"},{"key":"ref9","first-page":"1","article-title":"Reinforcement learning for sepsis treatment: Baselines and analysis","author":"raghu","year":"2019","journal-title":"Proc Reinforcement Learn Real Life"},{"key":"ref1","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref20","author":"xiao","year":"2019","journal-title":"Characterizing attacks on deep reinforcement learning"},{"key":"ref45","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2740965"},{"key":"ref47","author":"raffin","year":"2018","journal-title":"Reinforcement Learning Baseline Zoo"},{"key":"ref21","author":"kos","year":"2017","journal-title":"Delving into adversarial attacks on deep policies"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2006.883272"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2018.2796940"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2004.11.095"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2019.8789935"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2682274"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2664665"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2704118"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593362"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/9645278\/09003391.pdf?arnumber=9003391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:24Z","timestamp":1652194464000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003391\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":47,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2020.2974509","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12]]}}}