{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:36:46Z","timestamp":1763105806697,"version":"build-2065373602"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/aicas51828.2021.9458435","type":"proceedings-article","created":{"date-parts":[[2021,6,23]],"date-time":"2021-06-23T20:01:10Z","timestamp":1624478470000},"page":"1-4","source":"Crossref","is-referenced-by-count":5,"title":["Energy-Efficient Deep Reinforcement Learning Accelerator Designs for Mobile Autonomous Systems"],"prefix":"10.1109","author":[{"given":"Juhyoung","family":"Lee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changhyeon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghyeon","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangyeob","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangjin","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hoi-Jun","family":"Yoo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref13","article-title":"Seed rl: Scalable and efficient deep-rl with accelerated central inference","author":"espeholt","year":"2020","journal-title":"In International Conference on Learning Representations"},{"key":"ref14","article-title":"Challenges of real-world reinforcement learning","author":"dulac-arnold","year":"2019","journal-title":"arXiv preprint arXiv 1904 12848"},{"key":"ref15","article-title":"The ingredients of real world robotic reinforcement learning","author":"zhu","year":"2020","journal-title":"In International Conference on Learning Representations"},{"key":"ref16","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"clavera","year":"2019","journal-title":"In International Conference on Learning Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2019.8662447"},{"key":"ref18","article-title":"GST: Group-Sparse Training for Accelerating Deep Reinforcement Learning","author":"lee","year":"2021","journal-title":"arXiv 2101 09650"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1109\/DASC43569.2019.9081749","article-title":"Drone Navigation and Avoidance of Obstacles Through Deep Reinforcement Learning","author":"\u00e7etin","year":"2019","journal-title":"2019 IEEE\/AIAA 38th Digital Avionics Systems Conference (DASC)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206247"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abb9764"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.011"},{"key":"ref8","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"In Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref7","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"In Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2712561"},{"key":"ref9","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"}],"event":{"name":"2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems (AICAS)","start":{"date-parts":[[2021,6,6]]},"location":"Washington DC, DC, USA","end":{"date-parts":[[2021,6,9]]}},"container-title":["2021 IEEE 3rd International Conference on Artificial Intelligence Circuits and Systems (AICAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9458399\/9458400\/09458435.pdf?arnumber=9458435","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:42:38Z","timestamp":1652197358000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9458435\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/aicas51828.2021.9458435","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}