{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T05:24:50Z","timestamp":1751520290629,"version":"3.28.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191608","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"01-10","source":"Crossref","is-referenced-by-count":2,"title":["Dynamic Edge Caching via Online Meta-RL"],"prefix":"10.1109","author":[{"given":"Yinan","family":"Mao","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiji","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tsinghua-Berkeley Shenzhen Institute, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haochen","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua-Berkeley Shenzhen Institute, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3000415"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2596042"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2018.8362276"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3132156"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2894403"},{"key":"ref37","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155373"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2935683"},{"key":"ref31","first-page":"4767","article-title":"Multi-task reinforcement learning with soft modularization","volume":"33","author":"yang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref30","first-page":"1","article-title":"Meta-Q-learning","author":"fakoor","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350890"},{"key":"ref33","first-page":"1920","article-title":"Online meta learning","author":"finn","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2844985"},{"key":"ref32","first-page":"1","article-title":"Continuous adaptation via meta-learning in nonstationary and competitive environments","author":"al-shedivat","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC48107.2020.9148214"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2745201"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014902"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2403234"},{"key":"ref16","first-page":"1856","article-title":"Decoupling exploration and exploitation for meta-reinforcement learning without sacrifices","volume":"139","author":"liu","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1561\/2400000013"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2612123"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2015.7218445"},{"key":"ref24","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref23","first-page":"1","article-title":"Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO","author":"engstrom","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1800109"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2557804"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2541468.2541470"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MASS.2016.029"},{"key":"ref28","first-page":"1856","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","volume":"80","author":"haarnoja","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref29","first-page":"1","article-title":"R12: Fast reinforcement learning via slow reinforcement learning","author":"duan","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2017.7925848"},{"key":"ref7","first-page":"1352","article-title":"Lrfu: A spectrum of policies that subsumes the least recently used and least frequently used policies","volume":"50","author":"lee","year":"2001","journal-title":"IEEE Computer Architecture Letters"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2882583"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2447277"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2757761"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522722"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/954339.954341"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191608.pdf?arnumber=10191608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:42:14Z","timestamp":1692639734000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191608","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}