{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T04:48:15Z","timestamp":1751690895463,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:00:00Z","timestamp":1702425600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Swiss National Science Foundation","doi-asserted-by":"publisher","award":["51NF40_180545"],"award-info":[{"award-number":["51NF40_180545"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,13]]},"DOI":"10.1109\/cdc49753.2023.10383956","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:36Z","timestamp":1705689516000},"page":"2334-2339","source":"Crossref","is-referenced-by-count":1,"title":["Computationally Efficient Reinforcement Learning: Targeted Exploration leveraging Simple Rules"],"prefix":"10.1109","author":[{"given":"Loris","family":"Di Natale","sequence":"first","affiliation":[{"name":"Urban Energy Systems Lab,Empa,Dübendorf,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bratislav","family":"Svetozarevic","sequence":"additional","affiliation":[{"name":"Urban Energy Systems Lab,Empa,Dübendorf,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philipp","family":"Heer","sequence":"additional","affiliation":[{"name":"Urban Energy Systems Lab,Empa,Dübendorf,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Colin N.","family":"Jones","sequence":"additional","affiliation":[{"name":"Laboratoire d'Automatique,EPFL,Lausanne,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101964"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.17775\/cseejpes.2019.00920"},{"journal-title":"RL2: Fast reinforcement learning via slow reinforcement learning","year":"2016","author":"Duan","key":"ref3"},{"key":"ref4","article-title":"Pretraining representations for data-efficient reinforcement learning","volume":"34","author":"Schwarzer","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.115036"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA54724.2022.9831914"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25891-6_16"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/317"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS54341.2022.00021"},{"key":"ref12","article-title":"Towards safe online reinforcement learning in computer systems","volume-title":"33rd conference on neural information processing systems (NeurIPS 2019)","author":"Mao","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103662"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3179567"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3447555.3464874"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2276"},{"journal-title":"Safe exploration in continuous action spaces","year":"2018","author":"Dalal","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2022.07.619"},{"journal-title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","year":"2022","author":"Gu","key":"ref19"},{"issue":"1","key":"ref20","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":"ref21","article-title":"AlwaysSafe: Reinforcement learning without safety constraint violations during training","volume-title":"Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems","author":"Sim\u00e3o","year":"2021"},{"key":"ref22","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International conference on machine learning","author":"Achiam","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref24","first-page":"15931","article-title":"Learning to utilize shaping rewards: A new approach of reward shaping","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Hu","year":"2020"},{"volume-title":"Part 2: Kinds of RL Algorithms","year":"2018","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref27","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"International conference on machine learning","author":"Silver","year":"2014"},{"key":"ref28","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International Conference on Machine Learning","author":"Fujimoto","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.119806"},{"volume-title":"NEST","year":"2022","key":"ref30"}],"event":{"name":"2023 62nd IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2023,12,13]]},"location":"Singapore, Singapore","end":{"date-parts":[[2023,12,15]]}},"container-title":["2023 62nd IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10383192\/10383193\/10383956.pdf?arnumber=10383956","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:39:48Z","timestamp":1706027988000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10383956\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,13]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/cdc49753.2023.10383956","relation":{},"subject":[],"published":{"date-parts":[[2023,12,13]]}}}