{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:14:34Z","timestamp":1761894874019,"version":"build-2065373602"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209304","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["A Generalizable and Expressive Meta-Diffusion Policy for RTC Bandwidth Prediction"],"prefix":"10.1109","author":[{"given":"Zhiyuan","family":"Chen","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nuowen","family":"Kan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenglin","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenrui","family":"Dai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junni","family":"Zou","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongkai","family":"Xiong","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2017.2703615"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2910017.2910605"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604838"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419186"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483259"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3625468.3652183"},{"article-title":"Offline Reinforcement Learning with Implicit Q-Learning","year":"2021","author":"Kostrikov","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3625468.3652184"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3625468.3652174"},{"key":"ref10","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. ICML","author":"Fujimoto"},{"key":"ref11","first-page":"20132","article-title":"A Minimalist Approach to Offline Reinforcement Learning","volume-title":"Proc. NeurIPS","volume":"34","author":"Fujimoto"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3625468.3652177"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10228909"},{"key":"ref14","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. ICML","author":"Finn"},{"article-title":"Is conditional generative modeling all you need for decision-making?","year":"2022","author":"Ajay","key":"ref15"},{"article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","year":"2022","author":"Wang","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3625468.3653068"},{"key":"ref18","first-page":"61573","article-title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","volume-title":"Proc. NeurIPS","volume":"36","author":"Fujimoto"},{"article-title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","year":"2019","author":"Peng","key":"ref19"},{"key":"ref20","first-page":"67195","article-title":"Efficient Diffusion Policies For Offline Reinforcement Learning","volume-title":"Proc. NeurIPS","volume":"36","author":"Kang"},{"key":"ref21","first-page":"6840","article-title":"Denoising Diffusion Probabilistic Models","volume-title":"Proc. NeurIPS","volume":"33","author":"Ho"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209304.pdf?arnumber=11209304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:38:00Z","timestamp":1761889080000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209304\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209304","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}