{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T11:21:16Z","timestamp":1762341676123,"version":"3.37.3"},"reference-count":15,"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"}],"funder":[{"DOI":"10.13039\/100016311","name":"Arm","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/aicas51828.2021.9458548","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":1,"title":["An Energy-Efficient Hardware Accelerator for Hierarchical Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Aidin","family":"Shiri","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bharat","family":"Prakash","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arnab Neelim","family":"Mazumder","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicholas R.","family":"Waytowich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim","family":"Oates","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tinoosh","family":"Mohsenin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3301278"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2017.2690919"},{"key":"ref12","article-title":"A fast method to fine-tune neural networks for the least energy consumption on fpgas","author":"hosseini","year":"2021","journal-title":"Proceedings of the Hardware Aware Efficient Training workshop of ICLR 2021"},{"journal-title":"Automatic detection of respiratory symptoms using a low power multimodal cnn processor","year":"0","author":"mazumder","key":"ref13"},{"journal-title":"End-to-end scalable and low power multi-modal cnn for respiratory-related symptoms detection","year":"2020","author":"ren","key":"ref14"},{"key":"ref15","article-title":"Improving safety in reinforcement learning using model-based architectures and human intervention","author":"prakash","year":"2019","journal-title":"arXiv preprint arXiv 1903 01350"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MDAT.2021.3063363"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3386263.3407652"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3299874.3319493"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/OJCAS.2020.3043737"},{"journal-title":"Gym-Miniworld Environment for Openai Gym","year":"2018","author":"chevalier-boisvert","key":"ref8"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.10916","article-title":"The option-critic architecture","volume":"31","author":"bacon","year":"2017","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"article-title":"Learning behaviors from a single video demonstration using human feedback","year":"2019","author":"gandhi","key":"ref2"},{"key":"ref1","volume":"2","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"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\/09458548.pdf?arnumber=9458548","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T09:10:10Z","timestamp":1672564210000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9458548\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/aicas51828.2021.9458548","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}