- Title: Generalisation of Simulation-Based Search for Autonomous Gameplaying
- Speaker: Alexander Dockhorn
- Time and date: 4pm to 5pm, Feb 6, 2019
- Room: BR 3.02, Bancroft Road Teaching Rooms, QMUL Mile End Campus
On Wednesday 6th February 2019 the Game AI Group will host a seminar by Alexander Dockhorn from Otto-von-Guericke University Magdeburg. All welcome (especially students), no pre-booking required.
Abstract
In my talk, I am going to present how various supervised learning mechanisms can lead to an approximation of an unknown game’s forward model, allowing agents to apply simulation-based search algorithms to general game learning tasks. The presentation will include an analysis of game model characteristics and the resulting development of the forward model approximation framework. Various forward model learning systems will be explored to highlight capabilities and limitations of the discussed framework.
Bio
I am PhD student at the Otto-von-Guericke University. My current research interests are computational intelligence in games and intelligent data analysis. My focus is on partial information games as well as learning rules, game models and playing strategies from previous experiences.