{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T08:26:46Z","timestamp":1758961606037,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T00:00:00Z","timestamp":1679443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T00:00:00Z","timestamp":1679443200000},"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":[[2023,3,22]]},"DOI":"10.1109\/ciss56502.2023.10089771","type":"proceedings-article","created":{"date-parts":[[2023,4,10]],"date-time":"2023-04-10T18:58:36Z","timestamp":1681153116000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Distributed Policy Gradient with Heterogeneous Computations for Federated Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Ye","family":"Zhu","sequence":"first","affiliation":[{"name":"Auburn University,Department of Electrical and Computer Engineering,Auburn,USA"}]},{"given":"Xiaowen","family":"Gong","sequence":"additional","affiliation":[{"name":"Auburn University,Department of Electrical and Computer Engineering,Auburn,USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Federated learning: Collaborative machine learning without centralized training data","volume":"3","author":"McMahan","year":"2017","journal-title":"Google Research Blog"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.20517\/ir.2021.02"},{"key":"ref4","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":"ref5","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"International conference on machine learning","author":"Mnih","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29946-9_30"},{"journal-title":"Massively parallel methods for deep reinforcement learning","year":"2015","author":"Nair","key":"ref7"},{"key":"ref8","first-page":"278","article-title":"Learning to coordinate in multi-agent systems: A coordinated actor-critic algorithm and finite-time guarantees","volume-title":"Learning for Dynamics and Control Conference","author":"Zeng","year":"2022"},{"key":"ref9","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"International Conference on Machine Learning","author":"Zhang","year":"2018"},{"key":"ref10","article-title":"Finite-time convergence and sample complexity of multi-agent actor-critic reinforcement learning with average reward","volume-title":"International Conference on Learning Representations","author":"Hairi","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1900661"},{"key":"ref12","article-title":"Distral: Robust multitask reinforcement learning","volume":"30","author":"Teh","year":"2017","journal-title":"Advances in neural information processing systems"},{"journal-title":"Sample complexity of multi-task reinforcement learning","year":"2013","author":"Brunskill","key":"ref13"},{"key":"ref14","first-page":"18","article-title":"Federated reinforcement learning with environment heterogeneity","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Jin","year":"2022"},{"key":"ref15","first-page":"1002","article-title":"A decentralized policy gradient approach to multi-task reinforcement learning","author":"Zeng","year":"2021","journal-title":"Uncertainty in Artificial Intelligence"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-11748-0_15"},{"key":"ref17","first-page":"541","article-title":"An improved convergence analysis of stochastic variance-reduced policy gradient","author":"Xu","year":"2020","journal-title":"Uncertainty in Artificial Intelligence"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1613\/jair.806"},{"volume-title":"Technical Report","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2021.3078100"},{"key":"ref22","first-page":"10997","article-title":"Federated reinforcement learning: Linear speedup under markovian sampling","volume-title":"International Conference on Machine Learning","author":"Khodadadian","year":"2022"},{"key":"ref23","first-page":"4519","article-title":"Tighter theory for local sgd on identical and heterogeneous data","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Khaled","year":"2020"},{"volume-title":"On the sample complexity of reinforcement learning","year":"2003","author":"Kakade","key":"ref24"},{"key":"ref25","first-page":"4026","article-title":"Stochastic variance-reduced policy gradient","volume-title":"International conference on machine learning","author":"Papini","year":"2018"},{"key":"ref26","article-title":"Asynchronous parallel stochastic gradient for nonconvex optimization","volume":"28","author":"Lian","year":"2015","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","start":{"date-parts":[[2023,3,22]]},"location":"Baltimore, MD, USA","end":{"date-parts":[[2023,3,24]]}},"container-title":["2023 57th Annual Conference on Information Sciences and Systems (CISS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10089615\/10089616\/10089771.pdf?arnumber=10089771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T11:13:40Z","timestamp":1709464420000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10089771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,22]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ciss56502.2023.10089771","relation":{},"subject":[],"published":{"date-parts":[[2023,3,22]]}}}