Convergence of Actor-Critic with Multi-Layer Neural Networks

Published: 21 Sept 2023, Last Modified: 02 Nov 2023NeurIPS 2023 posterEveryoneRevisionsBibTeX
Keywords: Reinforcement Learning, Actor-Critic, gradient splitting, neural network
TL;DR: This paper establish a convergence result of Actor-Critic with neural network approximation.
Abstract: The early theory of actor-critic methods considered convergence using linear function approximators for the policy and value functions. Recent work has established convergence using neural network approximators with a single hidden layer. In this work we are taking the natural next step and establish convergence using deep neural networks with an arbitrary number of hidden layers, thus closing a gap between theory and practice. We show that actor-critic updates projected on a ball around the initial condition will converge to a neighborhood where the average of the squared gradients is $\tilde{O} \left( 1/\sqrt{m} \right) + O \left( \epsilon \right)$, with $m$ being the width of the neural network and $\epsilon$ the approximation quality of the best critic neural network over the projected set.
Submission Number: 8583