Reinforcement Learning - RO4100

Table of Content

  1. Foundations of Decision Making (Reward Hypothesis, Markov Property, Markov Reward Process, Value Iteration, Markov Decision Process, Policy Iteration, Bellman Equation.
  2. Principles of Reinforcement Learning (Generalize Policy Iteration, On & Off-policy learning, Monte-Carlo Approaches, (Multi-step) TD-Learning, Eligibility Traces, Exploration and Exploitation strategies)
  3. Deep Reinforcement Learning (Introduction to Deep Networks, Stochastic Gradient Descent, Function Approximation, Fitted Q-Iteration, (Double) Deep Q-Learning, Policy-Gradient approaches, open questions)

Teaching Objectives

  • Students get a comprehensive understanding of basic decision making theories, assumptions and methods.
  • Students understand and can apply advanced policy gradient methods to real world problems.
  • Students learn to analyze the challenges in a reinforcement learning application and to identify promising learning approaches.
  • The students will also experiment with the basic (deep) reinforcement learning methods and the simulation tools OpenAI Gym in accompanying exercises.

Contact Person