Aims and Fit of Module

This module aims to provide students an in-depth exploration of reinforcement learning (RL) techniques and their applications in various domains. By the end of this module, students will understand the foundations of much of modern RL techniques and be prepared to take more advanced courses or to apply AI tools and ideas to real-world problems.

Reinforcement learning is a subfield of artificial intelligence that focuses on training agents to make sequential decisions in dynamic environments. Through a combination of theoretical foundations, algorithmic understanding, and practical applications, students will
• understand how RL relates to and fits under the broader umbrella of machine learning, deep learning, supervised and unsupervised learning.
• understand the space of RL algorithms (Temporal- Difference learning, Monte Carlo, SARSA, Q-learning, Policy Gradient, and more).
• understand how to formalize your task as a RL problem, and how to begin implementing a solution. The tools learned in this module can be applied to game development (AI), customer interaction (how a website interacts with customers), smart assistants, recommender systems, supply chain, industrial control, finance, industrial control systems, and more.

Learning outcomes

A Systematically understand the fundamental concepts and principles of reinforcement learning
B Critically analyse real-life problem situations and expertly map them as reinforcement learning tasks
C Comprehensively understand advanced reinforcement learning techniques
D Develop the ability to design, implement and optimise reinforcement learning algorithms
E Systematically apply RL techniques to solve complex problems in various domains, such as robotics, game playing, or autonomous systems

Method of teaching and learning

The teaching philosophy of the module adopts the philosophy of Syntegrative Education. This has meant that the teaching delivery pattern, which follows more intensive block teaching, allows more meaningful contribution from industry partners. This philosophy is carried through also in terms of assessment, with reduction on the use of exams and increase in coursework, especially the use of problem-based assessment which is project focused. The delivery pattern provides space in the semester for students to concentrate on completing the assessments.

This module will be delivered through lectures, tutorials, and labs. Teaching will be conducted using problem-based learning, with problems and case-studies embedded in the lectures. Tutorial sessions are to assist students to develop practical skills in using tools and techniques commonly used in Reinforcement Learning so that they can confidently undertake an individual project in real-world problems. General transferable skills are developed through the presentation of written and oral reports.

In addition, students will be expected to devote unsupervised time to private study. Private study will provide time for reflection and consideration of lecture material and background reading.