{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T16:45:34Z","timestamp":1768322734880,"version":"3.49.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001858","name":"Vinnova","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561853","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"10734-10740","source":"Crossref","is-referenced-by-count":10,"title":["Using Reinforcement Learning to Create Control Barrier Functions for Explicit Risk Mitigation in Adversarial Environments"],"prefix":"10.1109","author":[{"given":"Edvards","family":"Scukins","sequence":"first","affiliation":[{"name":"SAAB,Aeronautics Division,Linköping,Sweden,SE-582 54"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Petter","family":"Ogren","sequence":"additional","affiliation":[{"name":"Royal Institute of Technology (KTH),Robotics, Perception and Learning Lab., School of Electrical Engineering and Computer Science,Stockholm,Sweden,SE-100 44"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.10744","article-title":"A deep hierarchical approach to lifelong learning in minecraft","author":"tessler","year":"2017","journal-title":"Thirty-First AAAI Conference on Artificial Intelligence"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1666"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-49674-9_8"},{"key":"ref13","article-title":"Uncertainty-aware reinforcement learning for collision avoidance","author":"kahn","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/RIVF.2019.8713624"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015384"},{"key":"ref16","article-title":"Autonomous aircraft sequencing and separation with hierarchical deep reinforcement learning","author":"brittain","year":"2018","journal-title":"Proceedings of the International Conference for Research in Air Transportation"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9030241"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref19","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2514\/6.2006-6197"},{"key":"ref6","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref5","first-page":"385","article-title":"Multiobjective reinforcement learning: A comprehensive overview","volume":"45","author":"liu","year":"2014","journal-title":"IEEE Transactions on Systems Man and Cybernetics Systems"},{"key":"ref8","article-title":"Learning and transfer of modulated locomotor controllers","author":"heess","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278776"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2638961"},{"key":"ref9","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","author":"vezhnevets","year":"0"},{"key":"ref20","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11797","article-title":"Safe reinforcement learning via shielding","author":"alshiekh","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref21","article-title":"Scipy: Open source scientific tools for python","author":"jones","year":"2001"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","location":"Xi'an, China","start":{"date-parts":[[2021,5,30]]},"end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561853.pdf?arnumber=9561853","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T22:50:39Z","timestamp":1673563839000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561853\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561853","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}