{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:55:41Z","timestamp":1780674941466,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,12]],"date-time":"2024-06-12T00:00:00Z","timestamp":1718150400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["Young Investigator Program Award, and grants #N00014-21-1-2225 and #N00014-22-1-2067"],"award-info":[{"award-number":["Young Investigator Program Award, and grants #N00014-21-1-2225 and #N00014-22-1-2067"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Cisco Systems","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"National Science Foundation","doi-asserted-by":"publisher","award":["#2127780, #2319198, #2321840, #2312517, and #2235472"],"award-info":[{"award-number":["#2127780, #2319198, #2321840, #2312517, and #2235472"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Semiconductor Research Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["#FA9550-22-1-0253"],"award-info":[{"award-number":["#FA9550-22-1-0253"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DARPA","award":["Young Faculty Award"],"award-info":[{"award-number":["Young Faculty Award"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,12]]},"DOI":"10.1145\/3649476.3658760","type":"proceedings-article","created":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T12:29:41Z","timestamp":1718022581000},"page":"111-118","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Efficient Exploration in Edge-Friendly Hyperdimensional Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8509-7803","authenticated-orcid":false,"given":"Yang","family":"Ni","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of California Irvine, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6757-015X","authenticated-orcid":false,"given":"William Y.","family":"Chung","sequence":"additional","affiliation":[{"name":"University of California, Irvine, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1247-2270","authenticated-orcid":false,"given":"Samuel","family":"Cho","sequence":"additional","affiliation":[{"name":"University of California, Irvine, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9057-8815","authenticated-orcid":false,"given":"Zhuowen","family":"Zou","sequence":"additional","affiliation":[{"name":"University of California, Irvine, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5761-0622","authenticated-orcid":false,"given":"Mohsen","family":"Imani","sequence":"additional","affiliation":[{"name":"University of California, Irvine, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,6,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Conference on learning theory. JMLR Workshop and Conference Proceedings, 39\u20131.","author":"Agrawal Shipra","year":"2012","unstructured":"Shipra Agrawal and Navin Goyal. 2012. Analysis of thompson sampling for the multi-armed bandit problem. In Conference on learning theory. JMLR Workshop and Conference Proceedings, 39\u20131."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISC253183.2021.9562941"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"e_1_3_2_1_4_1","volume-title":"Learning from Hypervectors: A Survey on Hypervector Encoding. arXiv preprint arXiv:2308.00685","author":"Aygun Sercan","year":"2023","unstructured":"Sercan Aygun, Mehran\u00a0Shoushtari Moghadam, 2023. Learning from Hypervectors: A Survey on Hypervector Encoding. arXiv preprint arXiv:2308.00685 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITA.2018.8503252"},{"key":"e_1_3_2_1_6_1","volume-title":"Openai gym. arXiv preprint arXiv:1606.01540","author":"Greg Brockman","year":"2016","unstructured":"Greg Brockman 2016. Openai gym. arXiv preprint arXiv:1606.01540 (2016)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM53951.2022.9786145"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3508352.3549437"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD56317.2022.00082"},{"key":"e_1_3_2_1_10_1","volume-title":"international conference on machine learning. PMLR, 1050\u20131059","author":"Gal Yarin","year":"2016","unstructured":"Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In international conference on machine learning. PMLR, 1050\u20131059."},{"key":"e_1_3_2_1_11_1","volume-title":"Multi-scale deep reinforcement learning for real-time 3D-landmark detection in CT scans","author":"Ghesu Florin-Cristian","year":"2017","unstructured":"Florin-Cristian Ghesu and Bogdan\u00a0others Georgescu. 2017. Multi-scale deep reinforcement learning for real-time 3D-landmark detection in CT scans. IEEE transactions on pattern analysis and machine intelligence 41, 1 (2017), 176\u2013189."},{"key":"e_1_3_2_1_12_1","volume-title":"International conference on machine learning. PMLR, 1352\u20131361","author":"Haarnoja Tuomas","year":"2017","unstructured":"Tuomas Haarnoja, Haoran Tang, Pieter Abbeel, and Sergey Levine. 2017. Reinforcement learning with deep energy-based policies. In International conference on machine learning. PMLR, 1352\u20131361."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2024.1371988"},{"key":"e_1_3_2_1_14_1","volume-title":"A Plug-in Tiny AI Module for Intelligent and Selective Sensor Data Transmission. arXiv preprint arXiv:2402.02043","author":"Huang Wenjun","year":"2024","unstructured":"Wenjun Huang, Arghavan Rezvani, Hanning Chen, Yang Ni, Sanggeon Yun, Sungheon Jeong, and Mohsen Imani. 2024. A Plug-in Tiny AI Module for Intelligent and Selective Sensor Data Transmission. arXiv preprint arXiv:2402.02043 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00028"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD56317.2022.00100"},{"key":"e_1_3_2_1_17_1","volume-title":"Hyperdimensional computing: An introduction to computing in distributed representation with high-dimensional random vectors. Cognitive computation 1, 2","author":"Kanerva Pentti","year":"2009","unstructured":"Pentti Kanerva. 2009. Hyperdimensional computing: An introduction to computing in distributed representation with high-dimensional random vectors. Cognitive computation 1, 2 (2009), 139\u2013159."},{"key":"e_1_3_2_1_18_1","volume-title":"RelHD: A Graph-based Learning on FeFET with Hyperdimensional Computing. In 2022 IEEE 40th International Conference on Computer Design (ICCD). IEEE, 553\u2013560","author":"Kang Jaeyoung","year":"2022","unstructured":"Jaeyoung Kang, Minxuan Zhou, 2022. RelHD: A Graph-based Learning on FeFET with Hyperdimensional Computing. In 2022 IEEE 40th International Conference on Computer Design (ICCD). IEEE, 553\u2013560."},{"key":"e_1_3_2_1_19_1","volume-title":"Optimizing online matching for ride-sourcing services with multi-agent deep reinforcement learning. arXiv preprint arXiv:1902.06228","author":"Jintao Ke","year":"2019","unstructured":"Jintao Ke 2019. Optimizing online matching for ride-sourcing services with multi-agent deep reinforcement learning. arXiv preprint arXiv:1902.06228 (2019)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3277593.3277617"},{"key":"e_1_3_2_1_21_1","volume-title":"Asymptotically efficient adaptive allocation rules. Advances in applied mathematics 6, 1","author":"Lai Tze\u00a0Leung","year":"1985","unstructured":"Tze\u00a0Leung Lai, Herbert Robbins, 1985. Asymptotically efficient adaptive allocation rules. Advances in applied mathematics 6, 1 (1985), 4\u201322."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933962"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66179-7_76"},{"key":"e_1_3_2_1_24_1","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-020-00510-8"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3091674"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the Great Lakes Symposium on VLSI","author":"Ni Yang","year":"2023","unstructured":"Yang Ni, Danny Abraham, 2023. Efficient Off-Policy Reinforcement Learning via Brain-Inspired Computing. In Proceedings of the Great Lakes Symposium on VLSI 2023. 449\u2013453."},{"key":"e_1_3_2_1_28_1","volume-title":"Brain-Inspired Trustworthy Hyperdimensional Computing with Efficient Uncertainty Quantification. In 2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD). IEEE, 01\u201309","author":"Ni Yang","year":"2023","unstructured":"Yang Ni, Hanning Chen, 2023. Brain-Inspired Trustworthy Hyperdimensional Computing with Efficient Uncertainty Quantification. In 2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD). IEEE, 01\u201309."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530668"},{"key":"e_1_3_2_1_30_1","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 292\u2013297","author":"Ni Yang","year":"2022","unstructured":"Yang Ni, Yeseong Kim, 2022. Algorithm-hardware co-design for efficient brain-inspired hyperdimensional learning on edge. In 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 292\u2013297."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3508352.3549477"},{"key":"e_1_3_2_1_32_1","volume-title":"Deep exploration via bootstrapped DQN. Advances in neural information processing systems 29","author":"Osband Ian","year":"2016","unstructured":"Ian Osband, Charles Blundell, Alexander Pritzel, and Benjamin Van\u00a0Roy. 2016. Deep exploration via bootstrapped DQN. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_1_33_1","volume-title":"International Conference on Machine Learning. PMLR, 2377\u20132386","author":"Osband Ian","year":"2016","unstructured":"Ian Osband, Benjamin Van\u00a0Roy, and Zheng Wen. 2016. Generalization and exploration via randomized value functions. In International Conference on Machine Learning. PMLR, 2377\u20132386."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2022.816294"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.757125"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-017-0942-6"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/1005332.1016794"},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the Great Lakes Symposium on VLSI","author":"Shahhosseini Sina","year":"2022","unstructured":"Sina Shahhosseini, Yang Ni, 2022. Flexible and personalized learning for wearable health applications using hyperdimensional computing. In Proceedings of the Great Lakes Symposium on VLSI 2022. 357\u2013360."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.sustainlp-1.4"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530395"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3371782"},{"key":"e_1_3_2_1_43_1","volume-title":"Machine learning 8, 3-4","author":"Watkins JCH","year":"1992","unstructured":"Christopher\u00a0JCH Watkins and Peter Dayan. 1992. Q-learning. Machine learning 8, 3-4 (1992), 279\u2013292."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iswa.2024.200353"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527422"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480958"}],"event":{"name":"GLSVLSI '24: Great Lakes Symposium on VLSI 2024","location":"Clearwater FL USA","acronym":"GLSVLSI '24","sponsor":["SIGDA ACM Special Interest Group on Design Automation"]},"container-title":["Proceedings of the Great Lakes Symposium on VLSI 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649476.3658760","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3649476.3658760","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649476.3658760","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649476.3658760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T02:29:23Z","timestamp":1755829763000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649476.3658760"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,12]]},"references-count":46,"alternative-id":["10.1145\/3649476.3658760","10.1145\/3649476"],"URL":"https:\/\/doi.org\/10.1145\/3649476.3658760","relation":{},"subject":[],"published":{"date-parts":[[2024,6,12]]},"assertion":[{"value":"2024-06-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}