Structure in Deep Reinforcement Learning: A Survey and Open Problems

TL;DR

This survey reviews how incorporating structural information into Deep Reinforcement Learning can address key challenges like data efficiency, generalization, safety, and interpretability, and proposes a unified framework for these methods.

Contribution

It unifies diverse approaches of integrating structure into RL under a single framework and introduces a design pattern perspective for future research.

Findings

Classifies methods of incorporating structure into RL.

Provides insights into challenges and potential solutions.

Lays groundwork for more effective RL algorithms.

Abstract

Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural Networks (DNNs) for function approximation, has demonstrated considerable success in numerous applications. However, its practicality in addressing various real-world scenarios, characterized by diverse and unpredictable dynamics, noisy signals, and large state and action spaces, remains limited. This limitation stems from poor data efficiency, limited generalization capabilities, a lack of safety guarantees, and the absence of interpretability, among other factors. To overcome these challenges and improve performance across these crucial metrics, one promising avenue is to incorporate additional structural information about the problem into the RL learning process. Various sub-fields of RL have proposed methods for incorporating such inductive biases. We amalgamate these diverse methodologies under a unified framework, shedding light on the role of structure in the learning problem, and classify these methods into distinct patterns of incorporating structure. By leveraging this comprehensive framework, we provide valuable insights into the challenges of structured RL and lay the groundwork for a design pattern perspective on RL research. This novel perspective paves the way for future advancements and aids in developing more effective and efficient RL algorithms that can potentially handle real-world scenarios better.