General course objectives

The objective of the course is to give students an introduction to reinforcement learning, classical system identification and control. Enable students to apply system identification, basic control methods and reinforcement learning for control in discrete and continuous systems.

Learning objectives

A student who has met the objectives of the course will be able to:

• Describe salient aspects of the control problem, open/closed loop control
• Formulate, analyze and control linear dynamical systems
• Apply linear adaptive control
• Formulate and apply dynamic programming
• Discuss assumptions of reinforcement learning in discrete systems
• Discuss assumptions of reinforcement learning in continuous systems
• Apply basic reinforcement learning paradigms for control in discrete and continuous domains
• Plan, carry out and report on a reinforcement learning project
• Present results and assessments in oral and writing
• Perform analysis and assessments in python

Content

The course consists of an introduction to

1. Introduction to identification and control strategies