Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization

30 September 2022

Papers citing "Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization"

7 / 7 papers shown

Title
Ordering-based Conditions for Global Convergence of Policy Gradient Methods Jincheng Mei Bo Dai Alekh Agarwal Mohammad Ghavamzadeh Csaba Szepesvári Dale Schuurmans 58 4 0 02 Apr 2025
First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach Andrew Wagenmaker Yifang Chen Max Simchowitz S. Du Kevin G. Jamieson 73 36 0 07 Dec 2021
Actor-critic is implicitly biased towards high entropy optimal policies Yuzheng Hu Ziwei Ji Matus Telgarsky 57 11 0 21 Oct 2021
Model-free Representation Learning and Exploration in Low-rank MDPs Aditya Modi Jinglin Chen A. Krishnamurthy Nan Jiang Alekh Agarwal OffRL 102 78 0 14 Feb 2021
Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes Guanghui Lan 91 136 0 30 Jan 2021
Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints Chi Jin Zhuoran Yang Zhaoran Wang OffRL 122 166 0 06 Jan 2021
On Linear Convergence of Policy Gradient Methods for Finite MDPs Jalaj Bhandari Daniel Russo 59 59 0 21 Jul 2020