{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T06:29:15Z","timestamp":1750746555103,"version":"3.37.3"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561645","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"10625-10631","source":"Crossref","is-referenced-by-count":2,"title":["Coding for Distributed Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Baoqian","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junfei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikolay","family":"Atanasov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref38","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2991361"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00137"},{"key":"ref30","first-page":"3368","article-title":"Gradient Coding: Avoiding Stragglers in Distributed Learning","author":"tandon","year":"2017","journal-title":"Proc of the 34th International Conference on Machine Learning"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-45391-9_11"},{"key":"ref35","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":"ref34","first-page":"486","article-title":"A theoretical analysis of deep q-learning","author":"fan","year":"2020","journal-title":"Learning for Dynamics and Control"},{"article-title":"Mean field multi-agent reinforcement learning","year":"2018","author":"yang","key":"ref10"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8006962"},{"key":"ref11","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"article-title":"Massively parallel methods for deep reinforcement learning","year":"2015","author":"nair","key":"ref12"},{"key":"ref13","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"article-title":"Reinforcement learning through asynchronous advantage actor-critic on a gpu","year":"2016","author":"babaeizadeh","key":"ref14"},{"year":"0","key":"ref15","article-title":"A2C"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.01.079"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2904055"},{"key":"ref18","first-page":"1223","article-title":"More effective distributed ml via a stale synchronous parallel parameter server","author":"ho","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"19","article-title":"Communication efficient distributed machine learning with the parameter server","author":"li","year":"2014","journal-title":"Advances in neural information processing systems"},{"article-title":"A locality-based approach for coded computation","year":"2020","author":"rudow","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref27","first-page":"1215","article-title":"Lagrange coded computing: Optimal design for resiliency, security, and privacy","author":"yu","year":"2019","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref3","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8006960"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref5"},{"key":"ref8","first-page":"871","article-title":"Extending q-learning to general adaptive multi-agent systems","author":"tesauro","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2017.123"},{"article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","year":"2017","author":"foerster","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989515"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2016.7541478"},{"year":"0","key":"ref45","article-title":"Amazon EC2 m5n.large instance"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2015.7447112"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8006963"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2307\/2314898"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.244"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2004.833807"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.2983411"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511791338"},{"key":"ref26","first-page":"710","article-title":"Coded Distributed Computing for Inverse Problems","author":"yang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2006.261736"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2736066"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561645.pdf?arnumber=9561645","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:47:07Z","timestamp":1652197627000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561645\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561645","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}