{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T10:18:27Z","timestamp":1730283507431,"version":"3.28.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T00:00:00Z","timestamp":1702512000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T00:00:00Z","timestamp":1702512000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,14]]},"DOI":"10.1109\/msn60784.2023.00093","type":"proceedings-article","created":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T17:53:49Z","timestamp":1719424429000},"page":"628-635","source":"Crossref","is-referenced-by-count":0,"title":["RLink: Accelerate On-Device Deep Reinforcement Learning with Inference Knowledge at the Edge"],"prefix":"10.1109","author":[{"given":"Tianyu","family":"Zeng","sequence":"first","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}]},{"given":"Xiaoxi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}]},{"given":"Daipeng","family":"Feng","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}]},{"given":"Jingpu","family":"Duan","sequence":"additional","affiliation":[{"name":"Institute of Future Networks, Southern University of Science and Technology,Shenzhen,China"}]},{"given":"Zhi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}]},{"given":"Xu","family":"Chen","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,School of Computer Science and Engineering,Guangzhou,China"}]}],"member":"263","reference":[{"article-title":"6g: The next hyper connected experience for all","volume-title":"Tech. Rep","year":"2020","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2918951"},{"volume-title":"6g white paper on edge intelligence","year":"2020","author":"Peltonen","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2021.9615100"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3232630"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3026589"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.3042320"},{"volume":"3","volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"volume":"5","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"ICML 2018","author":"Haarnoja","key":"ref15"},{"key":"ref16","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"18","author":"Chen","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Distributed prioritized experience replay","volume-title":"6th International Conference on Learning Representations, ICLR 2018-Conference Track Proceedings","author":"Horgan","key":"ref17"},{"volume":"4","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","volume-title":"ICML 2018","author":"Espeholt","key":"ref18"},{"article-title":"Seed rl: Scalable and efficient deep-rl with accelerated central inference","volume-title":"ICLR","author":"Espeholt","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2022.06.006"},{"key":"ref21","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"volume":"7","article-title":"Rllib: Abstractions for distributed reinforcement learning","volume-title":"ICML 2018","author":"Liang","key":"ref22"},{"article-title":"Ray: A distributed framework for emerging ai applications","volume-title":"Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2018","author":"Moritz","key":"ref23"},{"volume":"PartF168147-10","article-title":"Sample factory: Egocentric 3d control from pixels at 100000 fps with asynchronous reinforcement learning","volume-title":"ICML 2020","author":"Petrenko","key":"ref24"},{"key":"ref25","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref26","article-title":"Tianshou: A highly modularized deep reinforcement learning library","volume":"23","author":"Weng","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2986803"},{"volume-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967849"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.101.2100269"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3229419"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3267443"},{"article-title":"Clipper: A low-latency online prediction serving system","volume-title":"Proceedings of the 14th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2017","author":"Crankshaw","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3093336.3037698"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155237"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3527155"},{"volume-title":"Computer Architecture: A Quantitative Approach","year":"2017","author":"Hennessy","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"article-title":"Mujoco: A physics engine for modelbased control","volume-title":"IEEE IROS","author":"Todorov","key":"ref39"},{"volume-title":"Flower: A friendly federated learning research framework","year":"2020","author":"Beutel","key":"ref40"},{"volume-title":"Envpool: A highly parallel reinforcement learning environment execution engine","year":"2022","author":"Weng","key":"ref41"}],"event":{"name":"2023 19th International Conference on Mobility, Sensing and Networking (MSN)","start":{"date-parts":[[2023,12,14]]},"location":"Nanjing, China","end":{"date-parts":[[2023,12,16]]}},"container-title":["2023 19th International Conference on Mobility, Sensing and Networking (MSN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10566866\/10566894\/10566941.pdf?arnumber=10566941","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T05:24:35Z","timestamp":1719465875000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10566941\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,14]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/msn60784.2023.00093","relation":{},"subject":[],"published":{"date-parts":[[2023,12,14]]}}}