Simulation-Based Approach to General Game Playing

Abstract

The aim of General Game Playing (GGP) is to create intelligent agents that automatically learn how to play many different games at an expert level without any human intervention. The most successful GGP agents in the past have used traditional game-tree search com-bined with an automatically learned heuristic function for evaluating game states. In this paper we describe a GGP agent that instead uses a Monte Carlo/UCT sim-ulation technique for action selection, an approach re-cently popularized in computer Go. Our GGP agent has proven its effectiveness by winning last year’s AAAI GGP Competition. Furthermore, we introduce and em-pirically evaluate a new scheme for automatically learn-ing search-control knowledge for guiding the simula-tion playouts, showing that it offers significant benefits for a variety of games.