{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T19:35:03Z","timestamp":1773776103894,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"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":[[2024,7,10]]},"DOI":"10.23919\/acc60939.2024.10644621","type":"proceedings-article","created":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T17:56:19Z","timestamp":1725558979000},"page":"3576-3583","source":"Crossref","is-referenced-by-count":4,"title":["Physics-informed RL for Maximal Safety Probability Estimation"],"prefix":"10.23919","author":[{"given":"Hikaru","family":"Hoshino","sequence":"first","affiliation":[{"name":"University of Hyoto,Department of Electrical Materials and Engineering,Hyogo,Japan,671\u20132280"}]},{"given":"Yorie","family":"Nakahira","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA,USA,15213"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8815169"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/ACC53348.2022.9867675"},{"key":"ref3","article-title":"Safe exploration in reinforcement learning: Theory and applications in robotics","volume-title":"ETH Zurich","author":"Berkenkamp","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-73959-1_12"},{"key":"ref5","author":"Srinivasan","year":"2020","journal-title":"Learning to be safe: Deep RL with a safety critic"},{"key":"ref6","first-page":"8682","article-title":"Density constrained reinforcement learning","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Qin","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CISS56502.2023.10089763"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2021.3070252"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/wics.1539"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794107"},{"key":"ref11","article-title":"Policy gradient for coherent risk measures","volume":"28","author":"Tamar","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2008.03.027"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.10.045"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10409-021-01148-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-022-01939-z"},{"key":"ref16","first-page":"358","article-title":"A generalizable physics-informed learning framework for risk probability estimation","volume-title":"Proceedings of the 5th Annual Learning for Dynamics and Control Conference (L4DC)","author":"Wang","year":"2023"},{"key":"ref17","author":"Mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref18","author":"Banerjee","year":"2023","journal-title":"A survey on physics informed reinforcement learning: Review and open problems"},{"key":"ref19","volume-title":"Controlled Markov Processes and Viscosity Solutions","author":"Fleming","year":"2006"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.09.005"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1137\/22M1484201"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.08.006"},{"key":"ref23","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.03.016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(97)00128-3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793919"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610391"}],"event":{"name":"2024 American Control Conference (ACC)","location":"Toronto, ON, Canada","start":{"date-parts":[[2024,7,10]]},"end":{"date-parts":[[2024,7,12]]}},"container-title":["2024 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10644130\/10644150\/10644621.pdf?arnumber=10644621","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T07:06:53Z","timestamp":1725692813000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10644621\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":27,"URL":"https:\/\/doi.org\/10.23919\/acc60939.2024.10644621","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]}}}