Speaker: Prof. Simon M. Lucas, University of Essex
Date: Sep 11, 2017 5:00 PM BST
Many problems in game AI can be viewed as noisy optimisation problems, where the noise or uncertainty can stem from many sources, including: games which are naturally stochastic, agents which follow stochastic policies (such us Monte Carlo Tree Search or Rolling Horizon Evolution), and noise when evaluating the quality of games. The problems arise when trying to optimise agents to play games well, or just in a particular way, when trying to optimise heuristics for Monte Carlo Tree Search, and when trying to optimise games in order to provide a particular style of player experience (such as a game where the player has to react quickly, or has to plan strategically). The webinar will show examples of how these problems arise, and describe recent research in efficient noisy optimisation that uses novel model-based optimisation algorithms to provide efficient and effective search.
Simon M. Lucas is a professor of Artificial Intelligence and head of the School of Electronic Engineering and Computer Science at Queen Mary University of London. He holds a PhD degree (1991) in Electronics and Computer Science from the University of Southampton. His main research interests are games, evolutionary computation, and machine learning, and he has published widely in these fields with over 200 peer-reviewed papers. He is the inventor of the scanning n-tuple classifier, and is the founding Editor-in-Chief of the IEEE Transactions on Computational Intelligence and AI in Games.
Please register at:
After registering, you will receive a confirmation email containing information about joining the webinar.
Brought to you by GoToWebinar®
Webinars Made Easy®