Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved Complexity

30 March 2021

Papers citing "Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved Complexity"

8 / 8 papers shown

Title
Regularized Q-Learning with Linear Function Approximation Jiachen Xi Alfredo Garcia P. Momcilovic 76 2 0 26 Jan 2024
Variance Reduction for Deep Q-Learning using Stochastic Recursive Gradient Hao Jia Xiao Zhang Jun Xu Wei Zeng Hao Jiang Xiao Yan Ji-Rong Wen 52 3 0 25 Jul 2020
Finite-Time Performance Bounds and Adaptive Learning Rate Selection for Two Time-Scale Reinforcement Learning Harsh Gupta R. Srikant Lei Ying 51 86 0 14 Jul 2019
Finite-Time Error Bounds For Linear Stochastic Approximation and TD Learning R. Srikant Lei Ying 61 252 0 03 Feb 2019
SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path Integrated Differential Estimator Cong Fang C. J. Li Zhouchen Lin Tong Zhang 85 577 0 04 Jul 2018
A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimization Zhize Li Jian Li 60 116 0 13 Feb 2018
Asynchronous Methods for Deep Reinforcement Learning Volodymyr Mnih Adria Puigdomenech Badia M. Berk Mirza Alex Graves Timothy Lillicrap Tim Harley David Silver Koray Kavukcuoglu 189 8,833 0 04 Feb 2016
SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives Aaron Defazio Francis R. Bach Simon Lacoste-Julien ODL 128 1,823 0 01 Jul 2014