{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T22:51:05Z","timestamp":1752101465485,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T00:00:00Z","timestamp":1698537600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T00:00:00Z","timestamp":1698537600000},"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":[[2023,10,29]]},"DOI":"10.1109\/ieeeconf59524.2023.10477008","type":"proceedings-article","created":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T19:28:52Z","timestamp":1711999732000},"page":"629-633","source":"Crossref","is-referenced-by-count":3,"title":["Offline Reinforcement Learning for Wireless Network Optimization with Mixture Datasets"],"prefix":"10.1109","author":[{"given":"Kun","family":"Yang","sequence":"first","affiliation":[{"name":"University of Virginia,Department of Electrical and Computer Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Virginia,Department of Electrical and Computer Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Yang","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University,Department of Electrical Engineering,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shu-Ping","family":"Yeh","sequence":"additional","affiliation":[{"name":"Intel Corporation,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jerry","family":"Sydir","sequence":"additional","affiliation":[{"name":"Intel Corporation,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv preprint"},{"key":"ref2","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International Conference on Machine Learning","author":"Fujimoto","year":"2019"},{"key":"ref3","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","article-title":"Offline reinforcement learning with implicit Q-learning","author":"Kostrikov","year":"2021","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"A deep Q-learning method for downlink power allocation in multi-cell networks","author":"Ahmed","year":"2019","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761431"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2937438"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS50562.2020.9162925"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3051163"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2022.3185139"},{"key":"ref12","first-page":"27 395","article-title":"Policy finetuning: Bridging sample-efficient offline and online reinforcement learning","volume":"34","author":"Xie","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","article-title":"When should we prefer offline reinforcement learning over behavioral cloning?","author":"Kumar","year":"2022","journal-title":"arXiv preprint"},{"first-page":"4","article-title":"Simulation assumptions and parameters for FDD HeNB RF requirements","volume-title":"Tech. Rep. R","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2012.36"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2010.111910.091238"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2014.2328102"},{"article-title":"Near-optimal conservative exploration in reinforcement learning under episode-wise constraints","volume-title":"International Conference on Machine Learning","author":"Li","key":"ref19"}],"event":{"name":"2023 57th Asilomar Conference on Signals, Systems, and Computers","start":{"date-parts":[[2023,10,29]]},"location":"Pacific Grove, CA, USA","end":{"date-parts":[[2023,11,1]]}},"container-title":["2023 57th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10476702\/10476779\/10477008.pdf?arnumber=10477008","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T05:09:43Z","timestamp":1712034583000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10477008\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,29]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf59524.2023.10477008","relation":{},"subject":[],"published":{"date-parts":[[2023,10,29]]}}}