{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T15:37:24Z","timestamp":1782574644781,"version":"3.54.5"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413992","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"5040-5044","source":"Crossref","is-referenced-by-count":2,"title":["Byzantine-Resilient Decentralized TD Learning with Linear Function Approximation"],"prefix":"10.1109","author":[{"given":"Zhaoxian","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Ling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref31","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref30","article-title":"Iterative approximate Byzantine consensus in arbitrary directed graphs – part II: Synchronous and asynchronous systems","author":"vaidya","year":"2012"},{"key":"ref10","article-title":"Finite-time performance of distributed temporal difference learning with linear function approximation","author":"doan","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/357172.357176"},{"key":"ref12","article-title":"Adversary-resilient inference and machine learning: From distributed to decentralized","author":"yang","year":"2019"},{"key":"ref13","article-title":"A convergent O(n) algorithm for off-policy temporal-difference learning with linear function approximation","author":"sutton","year":"2008","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992701"},{"key":"ref17","article-title":"A finite time analysis of temporal difference learning with linear function approximation","author":"bhandari","year":"2018"},{"key":"ref18","article-title":"Finite-time error bounds for linear stochastic approximation and TD learning","author":"srikant","year":"2019","journal-title":"Proceedings of the Conference on Learning Theory"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3154503"},{"key":"ref28","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21236\/ADA558910"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2241057"},{"key":"ref6","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"2018","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref29","article-title":"Byzantine-resilient decentralized TD learning with linear function approximation","author":"wu","year":"2020"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref8","article-title":"Communication-efficient distributed reinforcement learning","author":"chen","year":"2018"},{"key":"ref7","article-title":"Multi-agent reinforcement learning via double averaging primal-dual optimization","author":"wai","year":"2018","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TRA.2004.824698"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"ref20","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","author":"yin","year":"2018"},{"key":"ref22","article-title":"Machine learning with adversaries: Byzantine tolerant gradient descent","author":"blanchard","year":"2017","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref21","article-title":"Phocas: Dimensional Byzantine-resilient stochastic gradient descent","author":"xie","year":"2018"},{"key":"ref24","article-title":"Byzantine stochastic gradient descent","author":"alistarh","year":"2018","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011544"},{"key":"ref26","article-title":"BRIDGE: Byzantine-resilient decentralized gradient descent","author":"yang","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2471755"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413992.pdf?arnumber=9413992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:58Z","timestamp":1652197258000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413992\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413992","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}