The State of Sparse Training in Deep Reinforcement Learning

TL;DR

This paper systematically investigates the application of sparse neural network training techniques in Deep Reinforcement Learning, demonstrating their advantages over dense networks in terms of efficiency and performance.

Contribution

It is the first comprehensive study to evaluate existing sparse training methods across various DRL agents and environments, revealing their benefits and potential for future improvements.

Findings

Sparse networks outperform dense networks at the same parameter count in DRL.

Sparse training improves learning efficiency in DRL environments.

Detailed analysis of DRL components reveals how sparsity impacts performance.

Abstract

The use of sparse neural networks has seen rapid growth in recent years, particularly in computer vision. Their appeal stems largely from the reduced number of parameters required to train and store, as well as in an increase in learning efficiency. Somewhat surprisingly, there have been very few efforts exploring their use in Deep Reinforcement Learning (DRL). In this work we perform a systematic investigation into applying a number of existing sparse training techniques on a variety of DRL agents and environments. Our results corroborate the findings from sparse training in the computer vision domain - sparse networks perform better than dense networks for the same parameter count - in the DRL domain. We provide detailed analyses on how the various components in DRL are affected by the use of sparse networks and conclude by suggesting promising avenues for improving the effectiveness of sparse training methods, as well as for advancing their use in DRL.