{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T18:39:56Z","timestamp":1765391996411,"version":"3.46.0"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3637842","type":"journal-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:59:03Z","timestamp":1764269943000},"page":"204743-204758","source":"Crossref","is-referenced-by-count":0,"title":["Evaluation of Efficient and Flexible Hardware\u2013Software Co-Design of Advantage Actor\u2013Critic Reinforcement Learning for Edge Deployment"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3481-7962","authenticated-orcid":false,"given":"Chavakorn","family":"Somjaisuk","sequence":"first","affiliation":[{"name":"Department of Engineering, Kochi University of Technology, Kami, Kochi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2134-5588","authenticated-orcid":false,"given":"Wang","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Engineering, Kochi University of Technology, Kami, Kochi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8151-0085","authenticated-orcid":false,"given":"Yukio","family":"Mitsuyama","sequence":"additional","affiliation":[{"name":"Department of Engineering, Kochi University of Technology, Kami, Kochi, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Reinforcement learning: An introduction, Nachdruck","volume-title":"Adaptive Computation and Machine Learning","author":"Sutton","year":"2014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/systems11110535"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-105157"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3477600"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0213-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2020.3014556"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref10","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/COINS49042.2020.9191634"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3146518"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref14","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. 13th Int. Conf. Neural Inf. Process. Syst.","author":"Sutton"},{"key":"ref15","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016","journal-title":"arXiv:1602.01783"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2885950"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3039902.3039915"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW50202.2020.00024"},{"key":"ref19","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM48280.2020.00012"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3134709"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304058"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2024.3353690"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-022-04117-z"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3562835"},{"key":"ref26","article-title":"An overview of gradient descent optimization algorithms","author":"Ruder","year":"2016","journal-title":"arXiv:1609.04747"},{"volume-title":"PYNQ-Python Productivity for Zynq","year":"2025","key":"ref27"},{"volume-title":"Ultra96-v2 Development Board","year":"2025","key":"ref28"},{"volume-title":"Vivado AXI Reference Guide","year":"2025","key":"ref29"},{"key":"ref30","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref31","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"Duan","year":"2016","journal-title":"arXiv:1604.06778"},{"key":"ref32","article-title":"Benchmarking model-based reinforcement learning","author":"Wang","year":"2019","journal-title":"arXiv:1907.02057"},{"key":"ref33","first-page":"8026","article-title":"PyTorch: An imperative style, high performance deep learning library","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Paszke"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11270932.pdf?arnumber=11270932","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T18:33:46Z","timestamp":1765391626000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11270932\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3637842","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}