{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T05:57:46Z","timestamp":1761631066970,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611316","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"2873-2879","source":"Crossref","is-referenced-by-count":5,"title":["Safety Optimized Reinforcement Learning via Multi-Objective Policy Optimization"],"prefix":"10.1109","author":[{"given":"Homayoun","family":"Honari","sequence":"first","affiliation":[{"name":"University of Victoria,Faculty of Engineering and Computer Science,Victoria,BC,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehran Ghafarian","family":"Tamizi","sequence":"additional","affiliation":[{"name":"University of Victoria,Faculty of Engineering and Computer Science,Victoria,BC,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Homayoun","family":"Najjaran","sequence":"additional","affiliation":[{"name":"University of Victoria,Faculty of Engineering and Computer Science,Victoria,BC,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1016\/j.engappai.2019.103360"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICRA48506.2021.9560769"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/IROS.2018.8593420"},{"issue":"1","key":"ref4","first-page":"1437","article-title":"A comprehensive survey on safe rein-forcement learning","volume":"16","author":"Garc\u0131a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1146\/annurev-control-042920-020211"},{"year":"2022","author":"Gu","article-title":"A review of safe reinforcement learning: Methods, theory and applications","key":"ref6"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1201\/9781315140223"},{"key":"ref8","article-title":"Nonlinear programming. athena scientific","author":"Bertesekas","year":"1999","journal-title":"Belmont, Massachusetts"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1162\/NECO_a_00600"},{"year":"2018","author":"Tessler","article-title":"Reward constrained policy optimization","key":"ref10"},{"key":"ref11","first-page":"15338","article-title":"First order constrained optimization in policy space","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","first-page":"9133","article-title":"Responsive safety in reinforcement learning by pid lagrangian methods","volume-title":"International Conference on Machine Learning","author":"Stooke"},{"year":"2020","author":"Srinivasan","article-title":"Learning to be safe: Deep rl with a safety critic","key":"ref13"},{"year":"2018","author":"Dalal","article-title":"Safe exploration in continuous action spaces","key":"ref14"},{"key":"ref15","first-page":"2608","article-title":"Towards safe reinforcement learning with a safety editor policy","volume":"35","author":"Yu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/CDC.2018.8619572"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/ICRA46639.2022.9812181"},{"key":"ref18","first-page":"13859","article-title":"Safe reinforcement learning by imagining the near future","volume":"34","author":"Thomas","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/LRA.2021.3070252"},{"volume-title":"Reinforcement learning: An introduction.","year":"2018","author":"Sutton","key":"ref20"},{"key":"ref21","first-page":"143","article-title":"Safe explo-ration for reinforcement learning","volume-title":"ESANN","author":"Hans"},{"key":"ref22","first-page":"11","article-title":"A distributional view on multi-objective policy optimization","volume-title":"International Conference on Machine Learning","author":"Abdolmaleki"},{"year":"2021","author":"Abdolmaleki","article-title":"On multi-objective policy optimization as a tool for reinforcement learning","key":"ref23"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1613\/jair.3987"},{"key":"ref25","article-title":"Safety gymnasium: A unified safe reinforcement learning benchmark","volume":"36","author":"Ji","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International conference on machine learning","author":"Achiam"},{"key":"ref27","article-title":"Bullet-safety-gym: A framework for constrained reinforcement learning","author":"Gronauer","year":"2022","journal-title":"mediaTUM, Tech. Rep."},{"year":"2023","author":"de Lazcano","article-title":"Gymnasium robotics","key":"ref28"},{"year":"2018","author":"Haarnoja","article-title":"Soft actor-critic algorithms and applications","key":"ref29"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2024,5,13]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611316.pdf?arnumber=10611316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:16:27Z","timestamp":1723349787000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611316\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611316","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}