Efficient Sample Reuse in Policy Gradients with Parameter-based Exploration

TL;DR

This paper introduces a novel policy gradient method that combines parameter-based exploration, importance sampling, and an optimal baseline to effectively reuse samples, reduce variance, and improve reinforcement learning in continuous action spaces.

Contribution

It presents a new policy gradient approach that integrates three techniques for efficient sample reuse and variance reduction, supported by theoretical analysis and extensive experiments.

Findings

Reduced variance of gradient estimates.

Effective sample reuse through importance sampling.

Improved policy learning performance.

Abstract

The policy gradient approach is a flexible and powerful reinforcement learning method particularly for problems with continuous actions such as robot control. A common challenge in this scenario is how to reduce the variance of policy gradient estimates for reliable policy updates. In this paper, we combine the following three ideas and give a highly effective policy gradient method: (a) the policy gradients with parameter based exploration, which is a recently proposed policy search method with low variance of gradient estimates, (b) an importance sampling technique, which allows us to reuse previously gathered data in a consistent way, and (c) an optimal baseline, which minimizes the variance of gradient estimates with their unbiasedness being maintained. For the proposed method, we give theoretical analysis of the variance of gradient estimates and show its usefulness through extensive experiments.