Learning Simulation Control in General Game-Playing Agents

13 years 8 months ago
Learning Simulation Control in General Game-Playing Agents
The aim of General Game Playing (GGP) is to create intelligent agents that can automatically learn how to play many different games at an expert level without any human intervention. One of the main challenges such agents face is to automatically learn knowledge-based heuristics in real-time, whether for evaluating game positions or for search guidance. In recent years, GGP agents that use Monte-Carlo simulations to reason about their actions have become increasingly more popular. For competitive play such an approach requires an effective search-control mechanism for guiding the simulation playouts. In here we introduce several schemes for automatically learning search guidance based on both statistical and reinforcement learning techniques. We compare the different schemes empirically on a variety of games and show that they improve significantly upon the current state-of-theart in simulation-control in GGP. For example, in the chesslike game Skirmish, which has proved a particularl...
Hilmar Finnsson, Yngvi Björnsson
Added 29 Oct 2010
Updated 29 Oct 2010
Type Conference
Year 2010
Where AAAI
Authors Hilmar Finnsson, Yngvi Björnsson
Comments (0)