Simple and optimal methods for stochastic variational inequalities, II:
Markovian noise and policy evaluation in reinforcement learning

v1v2v3v4 (latest)

Simple and optimal methods for stochastic variational inequalities, II: Markovian noise and policy evaluation in reinforcement learning

15 November 2020

Georgios Kotsalis

ArXiv (abs)PDF HTML

Papers citing "Simple and optimal methods for stochastic variational inequalities, II: Markovian noise and policy evaluation in reinforcement learning"

9 / 9 papers shown

Title
A simple uniformly optimal method without line search for convex optimization Tianjiao Li Guanghui Lan 107 25 0 16 Oct 2023
Networked Communication for Decentralised Agents in Mean-Field Games Patrick Benjamin Alessandro Abate FedML 173 2 0 05 Jun 2023
Policy Mirror Descent Inherently Explores Action Space Yan Li Guanghui Lan OffRL 125 8 0 08 Mar 2023
Smooth Monotone Stochastic Variational Inequalities and Saddle Point Problems: A Survey Aleksandr Beznosikov Boris Polyak Eduard A. Gorbunov D. Kovalev Alexander Gasnikov 88 31 0 29 Aug 2022
Optimal variance-reduced stochastic approximation in Banach spaces Wenlong Mou K. Khamaru Martin J. Wainwright Peter L. Bartlett Michael I. Jordan 85 9 0 21 Jan 2022
Accelerated and instance-optimal policy evaluation with linear function approximation Tianjiao Li Guanghui Lan A. Pananjady OffRL 91 13 0 24 Dec 2021
PER-ETD: A Polynomially Efficient Emphatic Temporal Difference Learning Method Ziwei Guan Tengyu Xu Yingbin Liang 85 4 0 13 Oct 2021
Cyclic Coordinate Dual Averaging with Extrapolation Chaobing Song Jelena Diakonikolas 100 8 0 26 Feb 2021
Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes Guanghui Lan 230 143 0 30 Jan 2021