{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:45:08Z","timestamp":1773773108150,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004489","name":"Mitacs","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004489","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802547","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"619-626","source":"Crossref","is-referenced-by-count":1,"title":["Meta SAC-Lag: Towards Deployable Safe Reinforcement Learning via MetaGradient-based Hyperparameter Tuning"],"prefix":"10.1109","author":[{"given":"Homayoun","family":"Honari","sequence":"first","affiliation":[{"name":"University of Victoria,Department of Mechanical Engineering,Victoria,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amir M.","family":"Soufi Enayati","sequence":"additional","affiliation":[{"name":"University of Victoria,Department of Mechanical Engineering,Victoria,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehran","family":"Ghafarian Tamizi","sequence":"additional","affiliation":[{"name":"University of Victoria,Department of Electrical and Computer Engineering,Victoria,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Homayoun","family":"Najjaran","sequence":"additional","affiliation":[{"name":"University of Victoria,Department of Mechanical Engineering,Victoria,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"110618","article-title":"Applications of reinforcement learning in energy systems","volume-title":"Renewable and Sustainable Energy Reviews","volume":"137","author":"Perera","year":"2021"},{"key":"ref2","article-title":"A survey of deep reinforcement learning in video games","author":"Shao","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3457538"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref7","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"ref8","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2019"},{"key":"ref9","article-title":"Meta-sac: Auto-tune the entropy temperature of soft actor-critic via metagradient","author":"Wang","year":"2020"},{"key":"ref10","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref12","volume":"4","author":"Bertsekas","year":"2012","journal-title":"Dynamic programming and optimal control: Volume I"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00600"},{"key":"ref14","first-page":"9133","article-title":"Responsive safety in reinforcement learning by pid lagrangian methods","volume-title":"International Conference on Machine Learning","author":"Stooke"},{"key":"ref15","article-title":"Reward constrained policy optimization","author":"Tessler","year":"2018"},{"key":"ref16","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International conference on machine learning","author":"Finn"},{"key":"ref17","article-title":"Meta-gradient reinforcement learning","volume":"31","author":"Xu","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.011"},{"key":"ref19","first-page":"29 861","article-title":"Discovery of options via meta-learned subgoals","volume":"34","author":"Veeriah","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","first-page":"20 913","article-title":"A self-tuning actor-critic algorithm","volume":"33","author":"Zahavy","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Balancing constraints and rewards with meta-gradient d4pg","author":"Calian","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3070252"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-011-0066-z"},{"key":"ref24","first-page":"13 859","article-title":"Safe reinforcement learning by imagining the near future","volume":"34","author":"Thomas","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","article-title":"Safe exploration in markov decision processes","author":"Moldovan","year":"2012"},{"key":"ref26","article-title":"Safe model-based reinforcement learning with stability guarantees","volume":"30","author":"Berkenkamp","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref27","article-title":"A lyapunov-based approach to safe reinforcement learning","volume":"31","author":"Chow","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref28","article-title":"On optimal generalizability in parametric learning","volume":"30","author":"Beirami","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","first-page":"1568","article-title":"Bilevel programming for hyperparameter optimization and meta-learning","volume-title":"International conference on machine learning","author":"Franceschi"},{"key":"ref30","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015"},{"key":"ref31","article-title":"An overview of gradient descent optimization algorithms","author":"Ruder","year":"2016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref33","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":"ref34","first-page":"270","article-title":"Gpu-accelerated robotic simulation for distributed reinforcement learning","volume-title":"Conference on Robot Learning","author":"Liang"},{"key":"ref35","article-title":"Conservative safety critics for exploration","author":"Bharadhwaj","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812181"},{"key":"ref37","article-title":"Gymnasium robotics","author":"de Lazcano","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611316"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3299252"},{"key":"ref40","first-page":"2016","article-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"Coumans"},{"key":"ref41","article-title":"robosuite: A modular simulation framework and benchmark for robot learning","author":"Zhu","year":"2020"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802547.pdf?arnumber=10802547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:01:18Z","timestamp":1735196478000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802547\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802547","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}