Geometry and convergence of natural policy gradient methods

3 November 2022

Papers citing "Geometry and convergence of natural policy gradient methods"

8 / 8 papers shown

Title
Optimal Rates of Convergence for Entropy Regularization in Discounted Markov Decision Processes Johannes Muller Semih Cayci 44 0 0 06 Jun 2024
A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence Carlo Alfano Rui Yuan Patrick Rebeschini 62 15 0 30 Jan 2023
Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization Carlo Alfano Patrick Rebeschini 54 13 0 30 Sep 2022
Conjugate Natural Selection Reilly P. Raab Luca de Alfaro Yang Liu 18 0 0 29 Aug 2022
The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs Johannes Muller Guido Montúfar 39 8 0 14 Oct 2021
Dimension-Free Rates for Natural Policy Gradient in Multi-Agent Reinforcement Learning Carlo Alfano Patrick Rebeschini 40 5 0 23 Sep 2021
Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes Guanghui Lan 91 136 0 30 Jan 2021
On Linear Convergence of Policy Gradient Methods for Finite MDPs Jalaj Bhandari Daniel Russo 59 59 0 21 Jul 2020