Accelerated Reinforcement Learning

TL;DR

This paper introduces the novel integration of Nesterov's acceleration into the actor-critic reinforcement learning algorithm, demonstrating improved convergence and performance on a scheduling task.

Contribution

It is the first to apply Nesterov's acceleration to actor-critic algorithms, enhancing convergence speed and effectiveness in reinforcement learning.

Findings

Accelerated actor-critic algorithm converges faster.

Experimental results show improved scheduling performance.

Nesterov's acceleration significantly outperforms non-accelerated methods.

Abstract

Policy gradient methods are widely used in reinforcement learning algorithms to search for better policies in the parameterized policy space. They do gradient search in the policy space and are known to converge very slowly. Nesterov developed an accelerated gradient search algorithm for convex optimization problems. This has been recently extended for non-convex and also stochastic optimization. We use Nesterov's acceleration for policy gradient search in the well-known actor-critic algorithm and show the convergence using ODE method. We tested this algorithm on a scheduling problem. Here an incoming job is scheduled into one of the four queues based on the queue lengths. We see from experimental results that algorithm using Nesterov's acceleration has significantly better performance compared to algorithm which do not use acceleration. To the best of our knowledge this is the first time Nesterov's acceleration has been used with actor-critic algorithm.