The AI that solves League of Legends: How to play a MOBA game professionally according to AI models
Y. Yao (TU Delft - Electrical Engineering, Mathematics and Computer Science)
G. Jongbloed – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)
R.J. Fokkink – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)
N. Parolya – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
This thesis examines the strategies used during the Ban/Pick phase of professional League of Legends matches by using a quantitative model to study its influencing variables, including win rates of champions, team compositions, team sides, and other components. By studying patterns and relationships between them, the purpose is to gain a deep understanding of decision-making techniques in this context, with which we aim to provide professional League of Legends coaches with state-of-the-art Ban/Pick strategies.
To achieve this, we first provide an introduction to the objectives and mechanisms of League of Legends before discussing the structure and rules of the Ban/Pick phase, which is often regarded as the most important aspect of game strategy within the game. We then discuss the methods and datasets used for quantitative analysis by comparing methods using different criteria and assessing their efficiency, consistency, and robustness. Finally, we summarize the results and recommend directions for further research.