{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T16:46:31Z","timestamp":1774716391569,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icra.2019.8794293","type":"proceedings-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T01:26:12Z","timestamp":1565659572000},"page":"8522-8528","source":"Crossref","is-referenced-by-count":51,"title":["Risk Averse Robust Adversarial Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Xinlei","family":"Pan","sequence":"first","affiliation":[]},{"given":"Daniel","family":"Seita","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[]},{"given":"John","family":"Canny","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","author":"wymann","year":"2000","journal-title":"TORCS The Open Racing Car Simulator"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"ref32","article-title":"Epopt: Learning robust neural network policies using model ensembles","author":"rajeswaran","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref31","article-title":"Parameter space noise for exploration","author":"plappert","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref30","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"2017","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref37","first-page":"1","article-title":"Learning the variance of the reward-to-go","volume":"17","author":"tamar","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref36","first-page":"484","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"et al"},{"key":"ref35","article-title":"Safe, multiagent, reinforcement learning for autonomous driving","author":"shalev-shwartz","year":"2016","journal-title":"arXiv preprint arXiv 1610 01292"},{"key":"ref34","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref10","article-title":"Gradient-free policy architecture search and adaptation","author":"ebrahimi","year":"2017","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref40","article-title":"Virtual to real reinforcement learning for autonomous driving","author":"you","year":"2017","journal-title":"British Machine Vision Conference"},{"key":"ref11","article-title":"Leave no trace: Learning to reset for safe and autonomous reinforcement learning","author":"eysenbach","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref12","article-title":"Noisy networks for exploration","author":"fortunato","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206247"},{"key":"ref14","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989680"},{"key":"ref16","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref17","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref18","article-title":"Learning end-to-end multimodal sensor policies for autonomous navigation","author":"liu","year":"2017","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206245"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.02.003"},{"key":"ref27","article-title":"Alternating optimisation and quadrature for robust control","author":"paul","year":"2018","journal-title":"AAAI 2018-The Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2012.6315483"},{"key":"ref6","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989190"},{"key":"ref5","article-title":"Emergent complexity via multi-agent competition","author":"bansal","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref8","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","author":"chow","year":"2018","journal-title":"Journal of Machine Learning Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487152"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461253"},{"key":"ref9","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref1","article-title":"Constrained policy optimization","author":"achiam","year":"2017","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref21","article-title":"Safe exploration in markov decision processes","author":"moldovan","year":"2012","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref24","first-page":"4026","article-title":"Deep exploration via bootstrapped dqn","author":"osband","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref23","article-title":"Risk sensitive reinforcement learning","author":"neuneier","year":"1998","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref26","article-title":"Robust deep reinforcement learning with adversarial attacks","author":"pattanaik","year":"2017","journal-title":"arXiv preprint arXiv 1712 03632"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"}],"event":{"name":"2019 International Conference on Robotics and Automation (ICRA)","location":"Montreal, QC, Canada","start":{"date-parts":[[2019,5,20]]},"end":{"date-parts":[[2019,5,24]]}},"container-title":["2019 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8780387\/8793254\/08794293.pdf?arnumber=8794293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:14:55Z","timestamp":1657854895000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8794293\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8794293","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}