{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:56:11Z","timestamp":1778345771424,"version":"3.51.4"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,7,9]],"date-time":"2023-07-09T00:00:00Z","timestamp":1688860800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,9]],"date-time":"2023-07-09T00:00:00Z","timestamp":1688860800000},"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":["62106147"],"award-info":[{"award-number":["62106147"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,7,9]]},"DOI":"10.1109\/icmlc58545.2023.10328010","type":"proceedings-article","created":{"date-parts":[[2023,11,28]],"date-time":"2023-11-28T14:04:26Z","timestamp":1701180266000},"page":"440-445","source":"Crossref","is-referenced-by-count":6,"title":["Federated Reinforcement Learning for Sharing Experiences Between Multiple Workers"],"prefix":"10.1109","author":[{"given":"Wenliang","family":"Feng","sequence":"first","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China,518060"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China,518060"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaogang","family":"Peng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University,Shenzhen,China,518060"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"243","article-title":"An alternative softmax operator for reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Asadi"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3172168"},{"key":"ref4","first-page":"18","article-title":"Federated reinforcement learning with environment heterogeneity","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Jin"},{"key":"ref5","first-page":"10997","article-title":"Federated reinforcement learning: Linear speedup under markovian sampling","volume-title":"International Conference on Machine Learning","author":"Khodadadian"},{"key":"ref6","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Kumar","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3083087"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2931179"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462901"},{"key":"ref10","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/AIKE.2019.00031"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.20517\/ir.2021.02"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/app9245571"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2986803"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3081626"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.enconman.2021.114381"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2022.3172336"},{"key":"ref20","article-title":"Federated deep reinforcement learning","author":"Zhuo","year":"2019","journal-title":"arXiv preprint"}],"event":{"name":"2023 International Conference on Machine Learning and Cybernetics (ICMLC)","location":"Adelaide, Australia","start":{"date-parts":[[2023,7,9]]},"end":{"date-parts":[[2023,7,11]]}},"container-title":["2023 International Conference on Machine Learning and Cybernetics (ICMLC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10327787\/10327919\/10328010.pdf?arnumber=10328010","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T17:50:50Z","timestamp":1761587450000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10328010\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,9]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icmlc58545.2023.10328010","relation":{},"subject":[],"published":{"date-parts":[[2023,7,9]]}}}