FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL Divergence-Reference-Cited by-同舟云学术

FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL Divergence

Author:

Xie Zhijie¹^ORCID,Song Shenghui¹^ORCID

Affiliation:

1. Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Sai kung, Hong Kong

Funder

NSFC/RGC Joint Research Scheme

Research Grants Council of the Hong Kong Special Administrative Region, China

National Natural Science Foundation of China

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Computer Networks and Communications

Link

Reference47 articles.

1. Deterministic policy gradient algorithms;silver;Proc 31st Int Conf Int Conf Mach Learn,2014

2. Trust region policy optimization;schulman;arXiv 1502 05477 [cs],2015

4. Fault-tolerant federated reinforcement learning with theoretical guarantee;fan;Proc Adv Neural Inf Process Syst,2021

5. Policy gradient methods for reinforcement learning with function approximation;sutton;Proc Adv Neural Inf Process Syst,2000

Cited by 17 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

4. Offline Reinforcement Learning Based on Next State Supervision;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

5. Federated Offline Reinforcement Learning;Journal of the American Statistical Association;2024-04