{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:48:45Z","timestamp":1730270925658,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"NSERC of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10342408","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"7545-7552","source":"Crossref","is-referenced-by-count":1,"title":["Dynamic Decision Frequency with Continuous Options"],"prefix":"10.1109","author":[{"given":"Amirmohammad","family":"Karimi","sequence":"first","affiliation":[{"name":"University of Alberta,Department of Computer Science,Edmonton,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Jin","sequence":"additional","affiliation":[{"name":"Huawei Technologies Canada,Noah's Ark Lab,Edmonton,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Luo","sequence":"additional","affiliation":[{"name":"Huawei Technologies Canada,Noah's Ark Lab,Edmonton,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. Rupam","family":"Mahmood","sequence":"additional","affiliation":[{"name":"University of Alberta,Department of Computer Science,Edmonton,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Jagersand","sequence":"additional","affiliation":[{"name":"University of Alberta,Department of Computer Science,Edmonton,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuele","family":"Tosatto","sequence":"additional","affiliation":[{"name":"University of Innsbruck,Digital Science Center,Department of Computer Science,Innsbruck,Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref1"},{"key":"ref2","article-title":"Continuous Control with Deep Reinforcement Learning","author":"Lillicrap","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref3","first-page":"1856","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","volume-title":"Proceeding of the 35th International Conference on Machine Learning","author":"Haarnoja","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9123.003.0009"},{"volume-title":"Markov decision processes: discrete stochastic dynamic programming","year":"2014","author":"Puterman","key":"ref5"},{"key":"ref6","first-page":"12009","article-title":"Continuous-time model-based reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Yildiz","year":"2021"},{"key":"ref7","article-title":"Thinking while moving: Deep reinforcement learning with concurrent control","volume-title":"International Conference on Learning Representations","author":"Xiao","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1994.374604"},{"key":"ref9","first-page":"6096","article-title":"Making deep q-learning methods robust to time discretization","volume-title":"International Conference on Machine Learning","author":"Tallec","year":"2019"},{"key":"ref10","article-title":"Locally persistent exploration in continuous control tasks with sparse rewards","author":"Amin","year":"2020","journal-title":"arXiv preprint"},{"key":"ref11","first-page":"267","article-title":"Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods","volume":"34","author":"Park","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560990"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10918"},{"key":"ref14","first-page":"6862","article-title":"Control frequency adaptation via action persistence in batch reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Metelli","year":"2020"},{"key":"ref15","article-title":"Learning to repeat: Fine Grained Action Repetition for Deep Reinforcement Learning","author":"Sharma","year":"2017","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref18","article-title":"Dac: The Double Actor-Critic Architecture for Learning Options","volume":"32","author":"Zhang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11831"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2018.8593894"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"ref22","first-page":"3742","article-title":"Unifying Task Specification in Reinforcement Learning","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"White","year":"2017"},{"key":"ref23","first-page":"2231","author":"Harutyunyan","year":"2019","journal-title":"The Termination Critic"},{"key":"ref24","first-page":"503","article-title":"Tree-Based Batch Mode Reinforcement Learning","volume":"6","author":"Ernst","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811771"},{"key":"ref27","article-title":"Deepmind control suite","author":"Tassa","year":"2018","journal-title":"arXiv preprint"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2023,10,1]]},"location":"Detroit, MI, USA","end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10342408.pdf?arnumber=10342408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T19:19:36Z","timestamp":1703013576000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10342408\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10342408","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}