{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T15:04:57Z","timestamp":1777388697804,"version":"3.51.4"},"reference-count":32,"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.2019.8794107","type":"proceedings-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T01:26:12Z","timestamp":1565659572000},"page":"8550-8556","source":"Crossref","is-referenced-by-count":72,"title":["Bridging Hamilton-Jacobi Safety Analysis and Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Jaime F.","family":"Fisac","sequence":"first","affiliation":[]},{"given":"Neil F.","family":"Lugovoy","sequence":"additional","affiliation":[]},{"given":"Vicenc","family":"Rubies-Royo","sequence":"additional","affiliation":[]},{"given":"Shromona","family":"Ghosh","sequence":"additional","affiliation":[]},{"given":"Claire J.","family":"Tomlin","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63387-9_5"},{"key":"ref31","article-title":"A Classification-based Approach for Approximate Reachability","author":"rubies-royo","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref10","article-title":"Human-level control through deep reinforcement learning","author":"mnih","year":"2015","journal-title":"Nature 518 7540"},{"key":"ref11","article-title":"Emergence of Locomotion Behaviours in Rich Environments","author":"heess","year":"2017","journal-title":"CoRR abs\/1707 02286"},{"key":"ref12","article-title":"Trust Region Policy Optimization","author":"schulman","year":"2015","journal-title":"CoRR abs\/1502 05477"},{"key":"ref13","article-title":"End-to-End Training of Deep Visuomotor Policies","author":"levine","year":"2015","journal-title":"CoRR abs\/1504 00702"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798979"},{"key":"ref15","article-title":"Safe exploration in Markov decision processes","author":"moldovan","year":"2012","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref16","article-title":"Constrained Policy Optimization","author":"achiam","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225136"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039601"},{"key":"ref19","article-title":"A general safety framework for learning-based control in uncertain robotic systems","author":"fisac","year":"2018","journal-title":"IEEE Transactions on Automatic Control (In Press)"},{"key":"ref28","article-title":"OpenAI Gym","author":"brockman","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref4","article-title":"Reach-avoid problems with time-varying dynamics, targets and constraints","author":"fisac","year":"2015","journal-title":"18th International Conference on Hybrid Systems Computation and Control (HSCC)"},{"key":"ref27","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"haarnoja","year":"2018","journal-title":"CoRR abs\/1801 01290"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.03.027"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1186\/s40687-016-0068-7"},{"key":"ref29","year":"2018","journal-title":"OpenAI OpenAI Five"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-31954-2_31","article-title":"A Toolbox of Hamilton-Jacobi Solvers for Analysis of Nondeterministic Continuous and Hybrid Systems","author":"mitchell","year":"2005","journal-title":"Hybrid Systems Computation and Control"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798268"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2828088"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2004.01.012"},{"key":"ref9","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2005.851439"},{"key":"ref20","article-title":"A Minimum Discounted Reward Hamilton-Jacobi Formulation for Computing Reachable Sets","author":"akametalu","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref22","article-title":"Theory of ordinary differential equations. Tata McGraw-Hill","author":"coddington","year":"1955"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref23","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"}],"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\/08794107.pdf?arnumber=8794107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:17:23Z","timestamp":1657855043000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8794107\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8794107","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}