{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:27:57Z","timestamp":1780054077321,"version":"3.54.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20209"],"award-info":[{"award-number":["U24A20209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"JST ASPIRE","award":["JPMJAP2325"],"award-info":[{"award-number":["JPMJAP2325"]}]},{"name":"JSPS Bilateral Joint Research Project","award":["JPJSB120231002"],"award-info":[{"award-number":["JPJSB120231002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw. Sci. Eng."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tnse.2025.3558747","type":"journal-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T18:03:25Z","timestamp":1744135405000},"page":"3244-3258","source":"Crossref","is-referenced-by-count":2,"title":["Age of Semantics in Cooperative Communications: To Expedite Simulation Towards Real via Offline Reinforcement Learning"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9453-4200","authenticated-orcid":false,"given":"Xianfu","family":"Chen","sequence":"first","affiliation":[{"name":"Shenzhen CyberAray Network Technology Company Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5479-7890","authenticated-orcid":false,"given":"Zhifeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang Lab, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7052-0007","authenticated-orcid":false,"given":"Shiwen","family":"Mao","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Auburn University, Auburn, AL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6853-5878","authenticated-orcid":false,"given":"Celimuge","family":"Wu","sequence":"additional","affiliation":[{"name":"Meta-Networking Research Center, The University of Electro-Communications, Chofu-shi, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1492-1364","authenticated-orcid":false,"given":"Honggang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Faculty of Data Science, City University of Macau, Taipa, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0261-0171","authenticated-orcid":false,"given":"Mehdi","family":"Bennis","sequence":"additional","affiliation":[{"name":"Centre for Wireless Communications, University of Oulu, Oulu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2013.2279895"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3372883"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2200016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3181986"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405887"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3182325"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2012.6195689"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2963667"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3126075"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.2991992"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3065072"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2017.8262777"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2018.8445981"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3155168"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3181038"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3135494"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2876279"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3065060"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3201751"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2937336"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.3005549"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3213227"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3087270"},{"key":"ref25","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2024"},{"key":"ref26","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2019"},{"key":"ref27","first-page":"1577","article-title":"Efficient online reinforcement learning with offline data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ball","year":"2023"},{"key":"ref28","article-title":"Keep doing what worked: Behavior modelling priors for offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Siegel","year":"2020"},{"key":"ref29","first-page":"7768","article-title":"Critic regularized regression","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2020"},{"key":"ref30","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29302"},{"key":"ref32","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2009.080818"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2019.2950624"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2009.5183474"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2013.2238607"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3144874"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2010.5430142"},{"key":"ref40","first-page":"328","article-title":"Sensitive discount optimality: Unifying discounted and average reward reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mahadevan","year":"1996"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.orl.2006.06.005"},{"key":"ref42","article-title":"Maximum entropy RL (provably) solves some robust RL problems","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Eysenbach","year":"2022"},{"key":"ref43","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"},{"key":"ref44","volume-title":"Dynamic Programming","author":"Bellman","year":"1957"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933893"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3079510"},{"key":"ref48","article-title":"Maximum a posteriori policy optimisation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Abdolmaleki","year":"2018"},{"key":"ref49","first-page":"9187","article-title":"ConQUR: Mitigating delusional bias in deep Q-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Su","year":"2020"},{"key":"ref50","article-title":"Ranking policy gradient","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20783"},{"key":"ref52","first-page":"28208","article-title":"Variational Bayesian reinforcement learning with regret bounds","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"O\u2019Donoghue","year":"2021"},{"key":"ref53","first-page":"15584","article-title":"Learning stochastic shortest path with linear function approximation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Min","year":"2022"},{"key":"ref54","first-page":"19645","article-title":"A state-distribution matching approach to non-episodic reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sharma","year":"2022"},{"key":"ref55","first-page":"2772","article-title":"Bridging the gap between value and policy based reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Nachum","year":"2017"},{"key":"ref56","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref58","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref59","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2000296"}],"container-title":["IEEE Transactions on Network Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488902\/11015837\/10955408.pdf?arnumber=10955408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T07:13:33Z","timestamp":1751094813000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10955408\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":60,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnse.2025.3558747","relation":{},"ISSN":["2327-4697","2334-329X"],"issn-type":[{"value":"2327-4697","type":"electronic"},{"value":"2334-329X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}