{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T10:35:12Z","timestamp":1760524512397,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160684","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"9435-9441","source":"Crossref","is-referenced-by-count":3,"title":["Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computers"],"prefix":"10.1109","author":[{"given":"Yan","family":"Wang","sequence":"first","affiliation":[{"name":"University of Alberta,Department of Computing Science,Edmonton,AB.,Canada,T6G 2E8"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gautham","family":"Vasan","sequence":"additional","affiliation":[{"name":"University of Alberta,Department of Computing Science,Edmonton,AB.,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,AB.,Canada,T6G 2E8"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Offline re-inforcement learning: Tutorial, review, and perspectives on open problems","author":"levine","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref12","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume":"33","author":"laskin","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","author":"ziebart","year":"2010","journal-title":"Carnegie Mellon University"},{"key":"ref15","first-page":"561","article-title":"Benchmarking reinforcement learning algorithms on real-world robots","author":"mahmood","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref14","first-page":"4635","article-title":"Setting up a reinforcement learning task with a real-world robot","author":"mahmood","year":"2018","journal-title":"In 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref20","article-title":"A walk in the park: Learning to walk in 20 minutes with model-free reinforcement learning","author":"smith","year":"2022","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/LRA.2019.2930489"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ICRA46639.2022.9811771"},{"key":"ref10","article-title":"Air learning: An ai research platform for algorithm-hardware benchmarking of autonomous aerial robots","author":"krishnan","year":"2019","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ICORR.2017.8009453"},{"year":"2018","author":"achiam","journal-title":"Spinning up in deep reinforcement learning","key":"ref2"},{"key":"ref1","article-title":"Maximum a pos-teriori policy optimisation","author":"abdolmaleki","year":"2018","journal-title":"In International Conference on Learning Representations"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref16","article-title":"Massively parallel methods for deep reinforcement learning","author":"nair","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref19","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref18","article-title":"Real-time reinforcement learning","volume":"32","author":"ramstedt","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep re-inforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"In International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.15607\/RSS.2019.XV.011"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/LRA.2016.2528294"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref3","article-title":"Towards real robot learning in the wild: A case study in bipedal locomotion","author":"bloesch","year":"2021","journal-title":"5th Annual Conference on Robot Learning"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/IROS.2016.7759557"},{"key":"ref5","article-title":"Large scale distributed deep networks","volume":"25","author":"dean","year":"2012","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2023,5,29]]},"location":"London, United Kingdom","end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10160684.pdf?arnumber=10160684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:36:12Z","timestamp":1690220172000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160684\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160684","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}