{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T07:01:33Z","timestamp":1779087693404,"version":"3.51.4"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iccad45719.2019.8942130","type":"proceedings-article","created":{"date-parts":[[2020,1,3]],"date-time":"2020-01-03T00:44:25Z","timestamp":1578012265000},"page":"1-7","source":"Crossref","is-referenced-by-count":23,"title":["Learning Deep Neural Network Controllers for Dynamical Systems with Safety Guarantees: Invited Paper"],"prefix":"10.1109","author":[{"given":"Jyotirmoy V.","family":"Deshmukh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James P.","family":"Kapinski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoya","family":"Yamaguchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danil","family":"Prokhorov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"ref3","first-page":"2361","article-title":"Safe policy search for lifelong reinforcement learning with sublinear regret","volume-title":"ICML","author":"Ammar","year":"2015"},{"key":"ref4","volume-title":"Concrete problems in ai safety","author":"Amodei","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ECC.2015.7330913"},{"key":"ref6","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","author":"Berkenkamp","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","volume-title":"Dynamic programming and optimal control","volume":"1","author":"Bertsekas","year":"1995"},{"key":"ref8","article-title":"Efsmt: A logical framework for the design of cyber-physical systems","author":"Cheng","year":"2014","journal-title":"Cyber-Physical System Architectures and Design Methodologies (CPSArch)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38574-2_14"},{"issue":"1","key":"ref11","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garcia","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref13","first-page":"565","article-title":"Reward shaping in episodic reinforcement learning","volume-title":"Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems, AAMAS \u201917","author":"Grze\u015b"},{"key":"ref14","volume-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17462-0_27"},{"key":"ref16","volume-title":"Logically-constrained reinforcement learning","author":"Hasanbeig","year":"2018"},{"key":"ref17","author":"Khalil","year":"2014","journal-title":"Nonlinear systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-96142-2_15"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref21","volume-title":"AI Safety gridworlds","author":"Leike","year":"2017"},{"key":"ref22","volume-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015"},{"key":"ref23","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"International conference on machine learning","author":"Mnih","year":"2016"},{"key":"ref24","article-title":"Linear and Nonlinear Programming","volume-title":"McGraw-Hill series in industrial engineering and management science","author":"Nash","year":"1996"},{"key":"ref25","first-page":"278","article-title":"Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping","volume-title":"Proceedings of the Sixteenth International Conference on Machine Learning, ICML \u201999","author":"Ng"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619142"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/10997703_2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2005.1470374"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2002.1184594"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039527"},{"key":"ref31","article-title":"EL2620: Nonlinear Control","author":"Schmidt","year":"2012","journal-title":"KTH Electrical Engineering"},{"key":"ref32","volume-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"Shalev-Shwartz","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CCTA.2018.8511342"},{"key":"ref34","first-page":"429","article-title":"Learning from Demonstration for Shaping Through Inverse Reinforcement Learning","volume-title":"Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems, AAMAS \u201916","author":"Suay"},{"key":"ref35","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref36","volume-title":"A survey of deep network solutions for learning control in robotics: From reinforcement to imitation","author":"Tai","year":"2016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3199852"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3199852"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354078"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3182\/20070822-3-ZA-2920.00076"},{"issue":"27","key":"ref41","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.ifacol.2015.11.152","article-title":"Robustness of control barrier functions for safety critical control","volume":"48","author":"Xiangru","year":"2015","journal-title":"IFAC-PapersOnLine"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"}],"event":{"name":"2019 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD)","location":"Westminster, CO, USA","start":{"date-parts":[[2019,11,4]]},"end":{"date-parts":[[2019,11,7]]}},"container-title":["2019 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8931666\/8942037\/08942130.pdf?arnumber=8942130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T00:30:33Z","timestamp":1706056233000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8942130\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iccad45719.2019.8942130","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}