{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T21:58:09Z","timestamp":1781560689572,"version":"3.54.5"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1849280,IIS-1849304"],"award-info":[{"award-number":["IIS-1849280,IIS-1849304"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981867","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"12919-12926","source":"Crossref","is-referenced-by-count":5,"title":["Scalable Safety-Critical Policy Evaluation with Accelerated Rare Event Sampling"],"prefix":"10.1109","author":[{"given":"Mengdi","family":"Xu","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peide","family":"Huang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengpei","family":"Li","sequence":"additional","affiliation":[{"name":"Columbia University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiacheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuewei","family":"Qi","sequence":"additional","affiliation":[{"name":"Toyota Motor North America R&D"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kentaro","family":"Oguchi","sequence":"additional","affiliation":[{"name":"Toyota Motor North America R&D"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyuan","family":"Huang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Henry","family":"Lam","sequence":"additional","affiliation":[{"name":"Columbia University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ding","family":"Zhao","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tra.2016.09.010"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561593"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2582208"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294636"},{"key":"ref6","article-title":"Rigorous agent evaluation: An adversarial approach to uncover catastrophic failures","author":"Uesato","year":"2018","journal-title":"arXiv preprint"},{"key":"ref7","first-page":"9827","article-title":"Scalable end-to-end autonomous vehicle testing via rare-event simulation","volume-title":"Advances in Neural Information Processing Systems","author":"OKelly","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2001.977305"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1060.0291"},{"key":"ref10","article-title":"Emergent complexity and zero-shot transfer via unsupervised environment design","author":"Dennis","year":"2020","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-28650-9_4"},{"key":"ref12","first-page":"2338","article-title":"Masked autoregressive flow for density estimation","volume-title":"Advances in Neural Information Processing Systems","author":"Papamakarios","year":"2017"},{"key":"ref13","volume-title":"An environment for autonomous driving decision-making","author":"Leurent","year":"2018"},{"key":"ref14","article-title":"Openai gym","author":"Brockman","year":"2016","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2701846"},{"key":"ref16","article-title":"Deep probabilistic accelerated evaluation: A certifiable rare-event simulation methodology for black-box autonomy","author":"Arief","year":"2020","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/07362990601139628"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3058873"},{"key":"ref19","article-title":"A survey of algorithms for black-box safety validation","author":"Corso","year":"2020","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Detecting overfitting via adversarial examples","author":"Werpachowski","year":"2019","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00175"},{"key":"ref22","first-page":"9668","article-title":"Towards optimal off-policy evaluation for reinforcement learning with marginalized importance sampling","volume-title":"Advances in Neural Information Processing Systems","author":"Xie","year":"2019"},{"key":"ref23","first-page":"1054","article-title":"Safe and efficient off-policy reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","author":"Munos","year":"2016"},{"key":"ref24","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","author":"Espeholt","year":"2018","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"1799","article-title":"Importance resampling for off-policy prediction","volume-title":"Advances in Neural Information Processing Systems","author":"Schlegel","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3291033"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-69033-9","volume-title":"Stochastic simulation: algorithms and analysis","volume":"57","author":"Asmussen","year":"2007"},{"key":"ref28","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Pinto","year":"2017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref30","volume-title":"Analysis and efficient simulation of queueing models of telecommunication systems","author":"de Boer","year":"2000"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref32","volume-title":"Minimalistic gridworld environment for openai gym","author":"Chevalier-Boisvert","year":"2018"},{"key":"ref33","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s13748-016-0094-0"},{"key":"ref35","first-page":"1952","article-title":"Online continual learning from imbalanced data","volume-title":"International Conference on Machine Learning","author":"Chrysakis"},{"key":"ref36","article-title":"Deep neural networks as gaussian processes","author":"Lee","year":"2017","journal-title":"arXiv preprint"},{"key":"ref37","first-page":"1193","article-title":"Local gaussian process regression for real time online model learning","volume-title":"Advances in neural information processing systems","volume":"21","author":"Nguyen-Tuong","year":"2008"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2008.4587201"},{"key":"ref39","article-title":"The variational gaussian process","author":"Tran","year":"2015","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.01.002"},{"key":"ref41","first-page":"6215","article-title":"Action robust reinforcement learning and applications in continuous control","volume-title":"International Conference on Machine Learning","author":"Tessler"},{"key":"ref42","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","author":"Zhang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1120.0540"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Kyoto, Japan","start":{"date-parts":[[2022,10,23]]},"end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981867.pdf?arnumber=9981867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:31:33Z","timestamp":1706758293000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981867\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981867","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}