{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T00:48:28Z","timestamp":1776127708653,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T00:00:00Z","timestamp":1716163200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T00:00:00Z","timestamp":1716163200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"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":[[2024,5,20]]},"DOI":"10.1109\/infocom52122.2024.10621347","type":"proceedings-article","created":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T17:25:41Z","timestamp":1723483541000},"page":"141-150","source":"Crossref","is-referenced-by-count":7,"title":["BR-DeFedRL: Byzantine-Robust Decentralized Federated Reinforcement Learning with Fast Convergence and Communication Efficiency"],"prefix":"10.1109","author":[{"given":"Jing","family":"Qiao","sequence":"first","affiliation":[{"name":"Shandong University,School of Computer Science and Technology,Qingdao,China"}]},{"given":"Zuyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"The George Washington University,Department of Electrical and Computer Engineering,DC,USA"}]},{"given":"Sheng","family":"Yue","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}]},{"given":"Yuan","family":"Yuan","sequence":"additional","affiliation":[{"name":"Shandong University,School of Computer Science and Technology,Qingdao,China"}]},{"given":"Zhipeng","family":"Cai","sequence":"additional","affiliation":[{"name":"Georgia State University,Department of Computer Science,Atlanta,GA,USA"}]},{"given":"Xiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shandong University,School of Computer Science and Technology,Qingdao,China"}]},{"given":"Ju","family":"Ren","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}]},{"given":"Dongxiao","family":"Yu","sequence":"additional","affiliation":[{"name":"Shandong University,School of Computer Science and Technology,Qingdao,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/s20051359"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3219644"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103149"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI56018.2022.00176"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3239815"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.20517\/ir.2021.02"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26281-4_29"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2196\/18477"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3339815"},{"key":"ref10","first-page":"1007","article-title":"Fault-tolerant federated reinforcement learning with theoretical guarantee","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021","author":"Fan"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3239542"},{"key":"ref12","first-page":"1002","article-title":"A decentralized policy gradient approach to multi-task reinforcement learning","volume-title":"Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, UAI 2021, Virtual Event, 27-30 July 2021","volume":"161","author":"Zeng"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5555\/2999611.2999647"},{"key":"ref14","article-title":"Learning bounds for importance weighting","author":"Cortes","year":"2010","journal-title":"NIPS"},{"key":"ref15","article-title":"Policy optimization via importance sampling","author":"Metelli","year":"2018","journal-title":"Neural Information Processing Systems"},{"key":"ref16","first-page":"4023","article-title":"Stochastic variance-reduced policy gradient","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10-15, 2018","volume":"80","author":"Papini"},{"key":"ref17","first-page":"541","article-title":"An improved convergence analysis of stochastic variance-reduced policy gradient","volume-title":"Proceedings of the Thirty-Fifth Conference on Uncertainty in Artificial Intelligence, UAI 2019, Tel Aviv, Israel, July 22-25, 2019","volume":"115","author":"Xu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-021-01847-3"},{"key":"ref19","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Advances in Neural Information Processing Systems","volume":"12","author":"Sutton","year":"1999"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1613\/jair.806"},{"key":"ref21","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015","volume":"37","author":"Schulman"},{"key":"ref22","article-title":"Challenges of real-world reinforcement learning","volume":"abs\/1904.12901","author":"Dulac-Arnold","year":"2019","journal-title":"CoRR"},{"key":"ref23","volume":"abs\/1507.04296","author":"Nair","year":"2015","journal-title":"Massively parallel methods for deep reinforcement learning"},{"key":"ref24","article-title":"Stochastic nested variance reduced gradient descent for nonconvex optimization","author":"Zhou","year":"2018","journal-title":"Neural Information Processing Systems"},{"key":"ref25","volume":"abs\/1807.01695","author":"Fang","year":"2018","journal-title":"Spider: Near-optimal nonconvex optimization via stochastic path integrated differential estimator"},{"key":"ref26","volume":"abs\/1708.04133","author":"Islam","year":"2017","journal-title":"Reproducibility of benchmarked deep reinforcement learning tasks for continuous control"},{"key":"ref27","volume":"abs\/2206.10185","author":"Khodadadian","year":"2022","journal-title":"Federated reinforcement learning: Linear speedup under markovian sampling"},{"key":"ref28","article-title":"Can decentralized algorithms outperform centralized algorithms? a case study for decentralized parallel stochastic gradient descent","author":"Lian","year":"2017","journal-title":"NIPS"},{"key":"ref29","article-title":"Openai gym","author":"Brockman","year":"2016"}],"event":{"name":"IEEE INFOCOM 2024 - IEEE Conference on Computer Communications","location":"Vancouver, BC, Canada","start":{"date-parts":[[2024,5,20]]},"end":{"date-parts":[[2024,5,23]]}},"container-title":["IEEE INFOCOM 2024 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10621050\/10621073\/10621347.pdf?arnumber=10621347","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T05:27:48Z","timestamp":1723526868000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10621347\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,20]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/infocom52122.2024.10621347","relation":{},"subject":[],"published":{"date-parts":[[2024,5,20]]}}}