Macquarie University
01whole.pdf (1.84 MB)

Optimal movement through a maze by an application of Q learning

Download (1.84 MB)
posted on 2022-03-28, 11:46 authored by Lu Han
Machine learning has become a very important aspect of the development of artificial intelligence (AI) in the world of computing. As a part of the machine learning techniques, reinforcement learning enables an agent to explore and study the unknown environment and through trial and error, the agent learns how to perform desired tasks in an optimum way. In this project, one of the methods to solve reinforcement problems, namely Q-learning, is studied and analysed. A maze problem is set up to count the learning time of an agent to travel from a fixed starting point A to destination B using Q-learning algorithm on Matlab platform. The learning time will be studied and then compared with different sets of maze of different size and complexity. Finally, a thorough discussion on the differences in the learning time and methods to further optimise the Q-learning algorithm will be provided. This document reports the outcome of this project and highlights the problems and challenges encountered and solutions devised.


Table of Contents

1. Introduction -- 2. Background theory -- 3. Q-learning algorithm -- 4. Experiment set up -- 5. Results and analysis -- 6. Conclusions and future work -- 7. Abbreviations -- Appendices -- Bibliography.


Bibliography: pages 91-93 Empirical thesis.

Awarding Institution

Macquarie University

Degree Type

Thesis bachelor honours


MRes, Macquarie University, Faculty of Science and Engineering, School of Engineering

Department, Centre or School

School of Engineering

Year of Award


Principal Supervisor

Sam Reisenfeld


Copyright Lu Han 2016. Copyright disclaimer:




1 online resource (xvi, 93 pages diagrams, graphs, tables)

Former Identifiers


Usage metrics

    Macquarie University Theses