Introduction to Reinforcement Learning

URL study guide

https://studiegids.vu.nl/en/courses/2024-2025/XB_0118

Course Objective

At the end of the course, students will:Understand and explain the fundamental concepts of reinforcement learning (RL), such as Markov decision process, value functions, etc. (Knowledge and understanding)Knowledge on different RL algorithms. (Knowledge and understanding)Characterize and differentiate between different RL algorithms (Temporal-Difference learning, Monte Carlo, SARSA, Q-learning, Policy Gradients, etc.). (Applying knowledge and understanding; Making judgments)Model a RL agent for sequential decision-making problems. (Applying knowledge and understanding)Implement RL algorithms in standard benchmarks. (Applying knowledge and understanding).

Course Content

Reinforcement Learning is one of the three main paradigms in machine learning, alongside supervised learning and unsupervised learning. It is a rapidly advancing field in artificial intelligence, focusing on how an agent can learn to maximize cumulative rewards while interacting with a complex and uncertain environment. Reinforcement Learning has diverse applications, including games, robotics, and general decision-making. This course offers a comprehensive introduction to the fundamental concepts of Reinforcement Learning. Topics will include key algorithms such as Monte Carlo, Temporal-Difference learning, SARSA, Q-learning, and Policy Gradients, among others.

Teaching Methods

Lectures (two per week) and working groups.

Method of Assessment

There will be a written exam which is supported by lectures (counting for 40%) and a group assignment (60%) of the final grade. There will be a resit exam, but NO resit for the group assignment.

Literature

Sutton, Richard S., and Andrew G. Barto. Reinforcement learning: An introduction. MIT press, 2018.

Target Audience

BSc Artificial Intelligence