{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T19:18:54Z","timestamp":1762024734731,"version":"build-2065373602"},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.23919\/acc45564.2020.9147381","type":"proceedings-article","created":{"date-parts":[[2020,7,27]],"date-time":"2020-07-27T22:02:33Z","timestamp":1595887353000},"page":"3953-3958","source":"Crossref","is-referenced-by-count":10,"title":["Toward Resilient Multi-Agent Actor-Critic Algorithms for Distributed Reinforcement Learning"],"prefix":"10.23919","author":[{"given":"Yixuan","family":"Lin","sequence":"first","affiliation":[]},{"given":"Shripad","family":"Gade","sequence":"additional","affiliation":[]},{"given":"Romeil","family":"Sandhu","sequence":"additional","affiliation":[]},{"given":"Ji","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1137\/0325070"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-32792-4"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029257"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619839"},{"key":"ref11","first-page":"1626","article-title":"Finite-time analysis of distributed TD(0) with linear function approximation on multi-agent reinforcement learning","author":"doan","year":"2019","journal-title":"36th International Conference on Machine Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2239000"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2013.6760239"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1982.1102924"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2014.7028492"},{"key":"ref16","first-page":"1039","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"hu","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref17","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"6379","article-title":"Multiagent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","author":"omidshafiei","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref28","first-page":"3521","article-title":"The hidden vulnerability of distributed learning in Byzantium","author":"el mhamdi","year":"2018","journal-title":"35th International Conference on Machine Learning"},{"key":"ref4","first-page":"535","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"2000","journal-title":"International Conference on Machine Learning"},{"key":"ref3","first-page":"195","article-title":"Planning, learning and coordination in multi-agent decision processes","author":"boutilier","year":"1996","journal-title":"9th conference on Theoretical aspects of rationality and knowledge"},{"article-title":"Fast and secure distributed learning in high dimension","year":"2019","author":"el mhamdi","key":"ref27"},{"key":"ref6","first-page":"1603","article-title":"Reinforcement learning to play an optimal Nash equilibrium in team Markov games","author":"wang","year":"2003"},{"key":"ref29","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-0417(01)00015-8"},{"key":"ref8","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2241057"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8430960"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619133"},{"key":"ref9","article-title":"A multiagent off-policy actor-critic algorithm for distributed reinforcement learning","author":"suttle","year":"2020","journal-title":"Proc 21st IFAC World Congress"},{"article-title":"Communication-efficient distributed reinforcement learning","year":"2018","author":"chen","key":"ref20"},{"article-title":"Generalized Byzantine tolerant SGD","year":"2018","author":"xie","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/357172.357176"},{"article-title":"Fall of empires: Breaking Byzantine-tolerant SGD by inner product manipulation","year":"2019","author":"xie","key":"ref24"},{"key":"ref23","first-page":"5650","article-title":"Byzantinerobust distributed learning: Towards optimal statistical rates","author":"yin","year":"2018","journal-title":"35th International Conference on Machine Learning"},{"key":"ref26","first-page":"119","article-title":"Machine learning with adversaries: Byzantine tolerant gradient descent","author":"blanchard","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"}],"event":{"name":"2020 American Control Conference (ACC)","start":{"date-parts":[[2020,7,1]]},"location":"Denver, CO, USA","end":{"date-parts":[[2020,7,3]]}},"container-title":["2020 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9140048\/9147203\/09147381.pdf?arnumber=9147381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,31]],"date-time":"2020-08-31T21:45:27Z","timestamp":1598910327000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9147381\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":33,"URL":"https:\/\/doi.org\/10.23919\/acc45564.2020.9147381","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}