YZV 415E - Deep Reinforcement Learning

Course Objectives

To introduce main methods in deep reinforcement learning
To be able to model decision making under uncertainty problems as Markov Decision Processes
To be able to design deep neural networks for deep reinforcement learning applications
To understand applications of deep reinforcement learning for autonomous systems

Course Description

Introduction to Reinforcement Learning, Markov Decision Processes, Dynamic Programming, Model Free Reinforcement Learning, Approximate Dynamic Programming and Reinforcement Learning, Deep Reinforcement Learning and Neural Networks, Exploration Strategies, Partially Observable Problems, Model Based Deep Reinforcement Learning, Applications for Autonomous Systems