Approximate Dynamic Programming and Reinforcement Learning

Content

Approximate Dynamic Programming (ADP) and Reinforcement Learning (RL) are two closely related paradigms for solving sequential decision making problems. ADP methods tackle the problems by developing optimal control methods that adapt to uncertain systems over time, while RL algorithms take the perspective of an agent that optimizes its behavior by interacting with its environment and learning from the feedback received. Both technologies have succeeded in applications of operation research, robotics, game playing, network management, and computational intelligence.

We will cover the following topics (not exclusively):

• Markov Decision Processes
• Dynamic programming
• Approximate Dynamic Programming
• Reinforcement Learning
• Policy Gradient Algorithms (if time permits)

On completion of this course, students are able to:

• describe classic scenarios in sequential decision making problems;
• explain basic models of ADP/RL methods;
• derive ADP/RL algorithms that are covered in the course;
• characterize convergence properties of the ADP/RL algorithms covered in the course;
• compare performance of the ADP/RL algorithms that are covered in the course;
•  select proper ADP/RL algorithms in accordance with specific applications.

Registration

The course communication will be handled through the moodle page and Rocket Chat. Use the link with guest access at the top to get to the course.

Register for the lecture and excercise. The question session is a placeholder in Tumonline and will take place whenever needed.