{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:49:09Z","timestamp":1772120949437,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100013373","name":"Alberta Machine Intelligence Institute (Amii)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100013373","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council (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":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9811771","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"5546-5552","source":"Crossref","is-referenced-by-count":12,"title":["Asynchronous Reinforcement Learning for Real-Time Control of Physical Robots"],"prefix":"10.1109","author":[{"given":"Yufeng","family":"Yuan","sequence":"first","affiliation":[{"name":"University of Alberta,Department of Computing Science,Edmonton,Canada,T6G 2E8"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. Rupam","family":"Mahmood","sequence":"additional","affiliation":[{"name":"University of Alberta,Department of Computing Science,Edmonton,Canada,T6G 2E8"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Deep reinforcement learning for robotic manipulation with asyn-chronous off-policy updates","author":"gu","year":"0","journal-title":"2017 IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.011"},{"key":"ref12","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref13","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref14","article-title":"Qt-opt: Scalable deep rein-forcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref15","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"kostrikov","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252823"},{"key":"ref17","article-title":"Reinforcement learning with augmented data","author":"laskin","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref18","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref19","article-title":"Setting up a reinforcement learning task with a real-world robot","author":"mahmood","year":"0","journal-title":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems"},{"key":"ref28","article-title":"Improving sample efficiency in model-free reinforcement learning from images","author":"yarats","year":"0","journal-title":"The AAAI Conference on Artificial Intelligence"},{"key":"ref4","article-title":"Safe exploration in continuous action spaces","author":"dalal","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref27","article-title":"Decoupling representation learning from reinforcement learning","author":"stooke","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-9958(58)80003-0"},{"key":"ref6","article-title":"An empirical investigation of the challenges of real-world reinforcement learning","author":"dulac-arnold","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref29","article-title":"The ingredients of real-world robotic reinforcement learning","author":"zhu","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref5","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref8","article-title":"Leave no trace: Learning to reset for safe and autonomous reinforcement learning","author":"eysenbach","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref7","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","author":"espeholt","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref2","article-title":"Distributed distributional deterministic policy gradients","author":"barth-maron","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref9","first-page":"512","article-title":"Deep spatial autoencoders for visuo-motor learning","author":"finn","year":"0","journal-title":"2016 IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref20","first-page":"561","article-title":"Benchmarking reinforcement learning algorithms on real-world robots","author":"mahmood","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref22","article-title":"Massively parallel methods for deep reinforcement learning","author":"nair","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref21","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref24","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.027"},{"key":"ref25","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09811771.pdf?arnumber=9811771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:03:53Z","timestamp":1667516633000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9811771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9811771","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}