{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:39:13Z","timestamp":1763192353124,"version":"3.45.0"},"reference-count":43,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227302","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Byzantine-Resilient Decentralized Parallel Policy Gradient"],"prefix":"10.1109","author":[{"given":"Qifeng","family":"Lin","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University"}]},{"given":"Yue","family":"Huang","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University"}]},{"given":"Qing","family":"Ling","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10651393"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29696"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3162550"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.108759"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2024.3411800"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10651491"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29946-9_30"},{"key":"ref8","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Mnih"},{"key":"ref9","first-page":"1007","article-title":"Fault-tolerant federated reinforcement learning with theoretical guarantee","volume":"34","author":"Fan","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3268475"},{"article-title":"Finite-time analysis of on-policy heterogeneous federated reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Zhang","key":"ref11"},{"article-title":"Massively parallel methods for deep reinforcement learning","year":"2015","author":"Nair","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2021.3078100"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2021.10.007"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123225"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2585302"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3049345"},{"key":"ref18","first-page":"5650","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","volume-title":"International Conference on Machine Learning","author":"Yin"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3154503"},{"article-title":"Phocas: Dimensional Byzantine-resilient stochastic gradient descent","year":"2018","author":"Xie","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3090952"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1613\/jair.806"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329179"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105992"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1003814"},{"key":"ref26","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"International Conference on Machine Learning","author":"Zhang"},{"key":"ref27","first-page":"1626","article-title":"Finite-time analysis of distributed TD(0) with linear function approximation on multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Doan"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3008139"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2021.108020"},{"article-title":"Byzantine-robust decentralized learning via self-centered clipping","year":"2022","author":"He","key":"ref30"},{"article-title":"Byzantine fault-tolerance in peer-to-peer distributed gradient-descent","year":"2021","author":"Gupta","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3116976"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747253"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3300629"},{"key":"ref35","first-page":"257","article-title":"On the hardness of decentralized multi-agent policy evaluation under byzantine attacks","volume-title":"International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks","author":"Fang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2024.3409676"},{"key":"ref37","first-page":"964","article-title":"Decentralized federated policy gradient with byzantine fault-tolerance and provably fast convergence","volume-title":"International Conference on Autonomous Agents and Multiagent Systems","author":"Jordan"},{"key":"ref38","article-title":"Reward poisoning on federated reinforcement learning","author":"Ma","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2005.1498447"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref41","first-page":"1329","article-title":"Bench-marking deep reinforcement learning for continuous control","volume-title":"International Conference on Machine Learning","author":"Duan"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2004.02.022"},{"key":"ref43","first-page":"4026","article-title":"Stochastic variance-reduced policy gradient","volume-title":"International Conference on Machine Learning","author":"Papini"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227302.pdf?arnumber=11227302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:36:40Z","timestamp":1763192200000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227302\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227302","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}