Introduction to Reinforcement Learning

Workshop

Slides Code

Date: May 29, 2025 10:00 AM – 13:00 PM
Event: Data Lab for Social Good Training Session
Location: Aberconway Building Meeting Room, Cardiff University, UK

Who is the course for?

This course is designed for researchers and postgraduate students who want to apply Reinforcement Learning (RL) to real-world decision-making in interdisciplinary settings, including supply chains, healthcare, and operational contexts across diverse industries. It is especially relevant for those working on problems involving sequential decision-making under uncertainty.

You don’t need prior RL knowledge, but you should be comfortable with basic probability and Python programming.

Learning Objectives

By the end of this workshop, participants will be able to:

• Understand the core ideas of RL in the context of healthcare decision-making
• Model sequential sequential decisions using Markov Decision Processes (MDPs)
• Apply key RL algorithms (Monte Carlo, SARSA, Q-learning) to learn optimal policies from experience
• Interpret learned policies and value functions in a healthcare context (e.g. when to treat, when to wait)
• Link RL insights to practical policy decisions like cost control, clinical risk, or stockout mitigation

Prerequisites

• Familiarity with basic probability and statistics (e.g., expected value, random variables)
• Some experience with Python, particularly with lists, dictionaries, and basic control flow
• No prior knowledge of RL or advanced machine learning is required