内容摘要：Statistical forward planning algorithms provide a simple and general way to provide competent AI controllers for a variety of games. Example algorithms include Monte Carlo Search, Monte Carlo Tree Search, and Rolling Horizon Evolution. They require that the game state can be copied and advanced (stepped forward) rapidly, a condition that is met in many cases. In this talk I will give a brief overview of the algorithms and then demonstrate the ability of rolling horizon evolution to play a variety of video games surprisingly well without the need for any training. This paves the way for automated play testing and analysis as a tool to assist games design, as well as providing decision support for complex real-world planning problems.

主讲人简介： Dr Simon Lucas is a professor of Artificial Intelligence and Head of the School of Electronic Engineering and Computer Science at Queen Mary University of London where he also heads the Game AI Research Group. He is the founding Editor-in-Chief of the IEEE Transactions on Games and he co-founded the IEEE Conference on Computational Intelligence and Games. He is currently the Vice-Principal for Education of the IEEE Computational Intelligence Society. His research involves developing and applying computational intelligence techniques to build better game AI, use AI to design better games, provide deep insights into the nature of intelligence and work towards Artificial General Intelligence.

此讲座为前沿课题讲座，欢迎全校师生踊跃参加。