Aims and Fit of Module

To introduce the techniques and concept of reinforcement learning. 
To develop the necessary skills to carry out and report simple experiments of reinforcement learning. 

Learning outcomes

A Demonstrate an understanding of recent advances in reinforcement learning. 
B Develop fundamental techniques of reinforcement learning. 
C Design and implement reinforcement learning algorithms to achieve the specified objectives, e.g., on performance and cost.
D Formulate and define practical engineering problems and apply reinforcement learning to analyze and solve the problems. 
E. Demonstrate understand and participation in the legal, social, ethical and professional framework in the development of reinforcement learning algorithms.

Method of teaching and learning

This module will be delivered through a combination of formal lectures, supervised laboratory sessions and tutorials. There are 3 lab reports that will be assigned across the semester. CW1 will assess students’ grasping basic knowledge of reinforcement learning (RL); CW2 will assess students’ understanding on basic algorithms of RL; CW3 will assess students’ mastery on comprehensive algorithms of RL.