Efficient Reinforcement Learning for Control
Files
TR Number
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The landscape of control systems has evolved rapidly with the emergence of Reinforcement Learning (RL), offering promising solutions to a wide range of dynamic decision-making problems. However, the application of RL to real-world control systems is often hindered by computational inefficiencies, scalability issues, and a lack of structure in learning mech- anisms. This thesis explores a central question: How can we design reinforcement learning algorithms that are not only effective but also computationally effi- cient and scalable for control systems of increasing complexity? To address this, we present a progression of approaches—starting with time-scale decomposition in small- scale systems and moving towards structured and adaptive learning strategies for large-scale, multi-agent control problems. Each chapter builds upon the previous one by introducing new methods tailored to the complexity and scale of the environment, culminating in a unified framework for efficient RL-driven control