{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T09:43:37Z","timestamp":1768902217110,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":12,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,5,13]],"date-time":"2019-05-13T00:00:00Z","timestamp":1557705600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"U.S. Army Research Laboratory","award":["W911NF-10-2-0022"],"award-info":[{"award-number":["W911NF-10-2-0022"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,5,13]]},"DOI":"10.1145\/3299874.3319493","type":"proceedings-article","created":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T12:10:25Z","timestamp":1558008625000},"page":"507-512","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["On the use of Deep Autoencoders for Efficient Embedded Reinforcement Learning"],"prefix":"10.1145","author":[{"given":"Bharat","family":"Prakash","sequence":"first","affiliation":[{"name":"University of Maryland, Baltimore County, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Horton","sequence":"additional","affiliation":[{"name":"University of Maryland, Baltimore County, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicholas R.","family":"Waytowich","sequence":"additional","affiliation":[{"name":"US Army Research Laboratory, Aberdeen, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William David","family":"Hairston","sequence":"additional","affiliation":[{"name":"US Army Research Laboratory, Aberdeen, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim","family":"Oates","sequence":"additional","affiliation":[{"name":"University of Maryland, Baltimore County, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tinoosh","family":"Mohsenin","sequence":"additional","affiliation":[{"name":"University of Maryland, Baltimore County, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,5,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Efficiently Combining Human Demonstrations and Interventions for Safe Training of Autonomous Systems in Real Time. AAAI Conference on Artificial Intelligence","author":"Goecks Vinicius G.","year":"2019","unstructured":"Vinicius G. Goecks, Gregory M. Gremillion, Vernon J. Lawhern, John Valasek, and Nicholas R. Waytowich. 2019. Efficiently Combining Human Demonstrations and Interventions for Safe Training of Autonomous Systems in Real Time. AAAI Conference on Artificial Intelligence (2019)."},{"key":"e_1_3_2_1_2_1","volume-title":"World models. arXiv preprint arXiv:1803.10122","author":"Ha David","year":"2018","unstructured":"David Ha and J\u00fcrgen Schmidhuber. 2018. World models. arXiv preprint arXiv:1803.10122 (2018)."},{"key":"e_1_3_2_1_3_1","volume-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. arXiv preprint arXiv:1801.01290","author":"Haarnoja Tuomas","year":"2018","unstructured":"Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, and Sergey Levine. 2018. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. arXiv preprint arXiv:1801.01290 (2018)."},{"key":"e_1_3_2_1_4_1","first-page":"1","article-title":"Sensornet: A scalable and low-power deep convolutional neural network for multimodal data classification","volume":"99","author":"Jafari Ali","year":"2018","unstructured":"Ali Jafari, Ashwinkumar Ganesan, Chetan Sai Kumar Thalisetty, Varun Sivasubramanian, Tim Oates, and Tinoosh Mohsenin. 2018. Sensornet: A scalable and low-power deep convolutional neural network for multimodal data classification. IEEE Transactions on Circuits and Systems I: Regular Papers 99 (2018), 1--14.","journal-title":"IEEE Transactions on Circuits and Systems I: Regular Papers"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045594"},{"key":"e_1_3_2_1_6_1","volume-title":"Nature","volume":"518","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, et al. 2015. Human-level control through deep reinforcement learning. Nature , Vol. 518, 7540 (2015), 529."},{"key":"e_1_3_2_1_7_1","unstructured":"Antonin Raffin and Roma Sokolkov. 2019. Learning to Drive Smoothly in Minutes. https:\/\/github.com\/araffin\/learning-to-drive-in-5-minutes\/. (2019)."},{"key":"e_1_3_2_1_8_1","volume-title":"Trial without Error: Towards Safe Reinforcement Learning via Human Intervention . (jul","author":"Saunders William","year":"2017","unstructured":"William Saunders, Girish Sastry, Andreas Stuhlmueller, and Owain Evans. 2017. Trial without Error: Towards Safe Reinforcement Learning via Human Intervention . (jul 2017). arxiv: 1707.05173 http:\/\/arxiv.org\/abs\/1707.05173"},{"key":"e_1_3_2_1_9_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","unstructured":"Richard S. Sutton David A. McAllester Satinder P. Singh and Yishay Mansour. 2000. Policy gradient methods for reinforcement learning with function approximation. In Advances in neural information processing systems. 1057--1063.","DOI":"10.5555\/3009657.3009806"},{"key":"e_1_3_2_1_11_1","volume-title":"Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces. AAAI Conference on Artificial Intelligence","author":"Warnell Garrett","year":"2018","unstructured":"Garrett Warnell, Nicholas Waytowich, Vernon Lawhern, and Peter Stone. 2018. Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces. AAAI Conference on Artificial Intelligence (2018), 1545--1553. https:\/\/aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16200"},{"key":"e_1_3_2_1_12_1","volume-title":"Lawhern","author":"Waytowich Nicholas R.","year":"2018","unstructured":"Nicholas R. Waytowich, Vinicius G. Goecks, and Vernon J. Lawhern. 2018. Cycle-of-Learning for Autonomous Systems from Human Interaction. CoRR , Vol. abs\/1808.09572v1 (2018). arxiv: 1808.09572v1 https:\/\/arxiv.org\/abs\/1808.09572v1"}],"event":{"name":"GLSVLSI '19: Great Lakes Symposium on VLSI 2019","location":"Tysons Corner VA USA","acronym":"GLSVLSI '19","sponsor":["SIGDA ACM Special Interest Group on Design Automation"]},"container-title":["Proceedings of the 2019 Great Lakes Symposium on VLSI"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3299874.3319493","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3299874.3319493","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3299874.3319493","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:38Z","timestamp":1750204418000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3299874.3319493"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,13]]},"references-count":12,"alternative-id":["10.1145\/3299874.3319493","10.1145\/3299874"],"URL":"https:\/\/doi.org\/10.1145\/3299874.3319493","relation":{},"subject":[],"published":{"date-parts":[[2019,5,13]]},"assertion":[{"value":"2019-05-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}