10 citations · 11 across the 5 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023★ 10 cited
Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates
Guangchen Lan, Han Wang, James Anderson +2
Federated reinforcement learning (FedRL) enables agents to collaboratively train a global policy without sharing their individual data. However, high communication overhead remains…
math.OC2023
Oracle Complexity Reduction for Model-free LQR: A Stochastic Variance-Reduced Policy Gradient Approach
Leonardo F. Toso, Han Wang, James Anderson
We investigate the problem of learning an -approximate solution for the discrete-time Linear Quadratic Regulator (LQR) problem via a Stochastic Variance-Reduced Policy Gradient…