{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:41:00Z","timestamp":1740102060409,"version":"3.37.3"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"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","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100013373","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191867","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Reducing the Cost of Cycle-Time Tuning for Real-World Policy Optimization"],"prefix":"10.1109","author":[{"given":"Homayoon","family":"Farrahi","sequence":"first","affiliation":[{"name":"University of Alberta,Department of Computing Science,Edmonton,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. Rupam","family":"Mahmood","sequence":"additional","affiliation":[{"name":"University of Alberta,Department of Computing Science,Edmonton,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Learning to walk via deep reinforcement learning","author":"haarnoja","year":"2018","journal-title":"Robotics Science Syst XV"},{"key":"ref12","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref15","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"3rd International Conference on Learning Representations"},{"key":"ref14","article-title":"SLM lab: A comprehensive benchmark and modular software framework for reproducible deep reinforcement learning","author":"keng","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561384"},{"key":"ref10","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1994.374604"},{"key":"ref1","article-title":"Solving rubik's cube with a robot hand","author":"akkaya","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref17","article-title":"Benchmarking reinforcement learning algorithms on real-world robots","author":"mahmood","year":"0","journal-title":"Proceedings of the 2nd Annual Conference on Robot Learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109421"},{"key":"ref19","article-title":"Generalized state-dependent exploration for deep reinforcement learning in robotics","author":"raffin","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref18","first-page":"771","article-title":"Policy gradient in continuous time","volume":"7","author":"munos","year":"2006","journal-title":"Journal of Machine Learning Research"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref23","article-title":"Making deep Q-learning methods robust to time discretization","author":"tallec","year":"0","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2018.00079"},{"key":"ref25","article-title":"dm_control: Software and tasks for continuous control","author":"tassa","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref20","article-title":"Real-time reinforcement learning","author":"ramstedt","year":"2019","journal-title":"Advances in neural information processing systems"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref22"},{"key":"ref21","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"journal-title":"Investigating two policy gradient methods under different time discretizations","year":"2021","author":"farrahi","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref9","article-title":"At human speed: Deep reinforcement learning with action delay","author":"firoiu","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.015"},{"key":"ref3","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"journal-title":"Pybullet a python module for physics simulation for games robotics and machine learning","year":"2016","author":"coumans","key":"ref5"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191867.pdf?arnumber=10191867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:43:31Z","timestamp":1692639811000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191867\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191867","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}