The Role of Deep Learning Regularizations on Actors in Offline RL

TL;DR

This paper investigates how deep learning regularizations like dropout and weight decay affect actor networks in offline reinforcement learning, showing they improve performance by around 6% on average.

Contribution

It provides the first empirical analysis of regularization effects on actor networks in offline RL, demonstrating consistent performance gains.

Findings

Regularization improves offline RL actor performance by 6%.

Standard techniques like dropout and weight decay are effective.

Enhances generalization in offline RL actor networks.

Abstract

Deep learning regularization techniques, such as dropout, layer normalization, or weight decay, are widely adopted in the construction of modern artificial neural networks, often resulting in more robust training processes and improved generalization capabilities. However, in the domain of Reinforcement Learning (RL), the application of these techniques has been limited, usually applied to value function estimators (Hiraoka et al., 2021; Smith et al., 2022), and may result in detrimental effects. This issue is even more pronounced in offline RL settings, which bear greater similarity to supervised learning but have received less attention. Recent work in continuous offline RL (Park et al., 2024) has demonstrated that while we can build sufficiently powerful critic networks, the generalization of actor networks remains a bottleneck. In this study, we empirically show that applying standard regularization techniques to actor networks in offline RL actor-critic algorithms yields improvements of 6% on average across two algorithms and three different continuous D4RL domains.