04-800-Y   Adaptive Control and Reinforcement Learning

Course description

The course objective is to train students who are interested in building intelligent systems capable of interacting and adapting to their environment. It will introduce different control techniques that are fundamental to building complex adaptive systems. This course will give an introduction and an overview of the theoretical and practical aspects of adaptive control behaviors both from the control perspective and the learning perspective.

Learning objectives

• Formalize problems as Markov Decision Processes
• Use of policy and value iteration for optimal decision-making
• Use various control algorithms for a wide range of applications (e.g., imitation learning, iterative learning, Q-learning, linear quadratic regulators, etc.)
• Understand the tradeoff between exploration and exploitation
• Use of policy and value iteration for optimal decision-making

Outcomes

After completing the course, students will have a good understanding of adaptive techniques, their strengths, and their limitations. Students will have the active knowledge needed to design and build intelligent agents capable of adapting in dynamic environments.

Content details

The topics that will be covered in this course include but are not limited to:

• optimal control
• model predictive control
• iterative learning control
• adaptive control
• reinforcement learning
• imitation learning
• approximate dynamic programming
• parameter estimation
• stability analysis

Faculty

Moise Busogi