A Tour of Reinforcement Learning: The View from Continuous Control

TL;DR

This survey explores reinforcement learning for continuous control, comparing methods through theoretical insights and a case study on LQR, highlighting the importance of models and challenges in safe, reliable learning.

Contribution

It provides a comprehensive overview of reinforcement learning in continuous control, integrating learning theory and control techniques, with a detailed case study on LQR performance analysis.

Findings

Non-asymptotic performance characterizations match experimental results.

Models and generality significantly impact reinforcement learning effectiveness.

Challenges remain in designing safe, reliable learning systems for complex environments.

Abstract

This manuscript surveys reinforcement learning from the perspective of optimization and control with a focus on continuous control applications. It surveys the general formulation, terminology, and typical experimental implementations of reinforcement learning and reviews competing solution paradigms. In order to compare the relative merits of various techniques, this survey presents a case study of the Linear Quadratic Regulator (LQR) with unknown dynamics, perhaps the simplest and best-studied problem in optimal control. The manuscript describes how merging techniques from learning theory and control can provide non-asymptotic characterizations of LQR performance and shows that these characterizations tend to match experimental behavior. In turn, when revisiting more complex applications, many of the observed phenomena in LQR persist. In particular, theory and experiment demonstrate the role and importance of models and the cost of generality in reinforcement learning algorithms. This survey concludes with a discussion of some of the challenges in designing learning systems that safely and reliably interact with complex and uncertain environments and how tools from reinforcement learning and control might be combined to approach these challenges.