GGP with Advanced Reasoning and Board Knowledge Discovery

TL;DR

This paper introduces mGDL, a simplified GDL variant for efficient reasoning, along with spatial features and genetic algorithms to enhance game knowledge, resulting in faster reasoning and improved game-playing performance.

Contribution

It presents mGDL for scalable reasoning, a GDL-to-C++ translation scheme, spatial features inspired by Go, and a genetic algorithm for parameter tuning, advancing GGP techniques.

Findings

GDL rule sheets mostly conform to mGDL with minor modifications.

Translation scheme achieves up to 7300% speedup over Prolog.

Spatial features improve win rates by up to 20%.

Abstract

Quality of General Game Playing (GGP) matches suffers from slow state-switching and weak knowledge modules. Instantiation and Propositional Networks offer great performance gains over Prolog-based reasoning, but do not scale well. In this publication mGDL, a variant of GDL stripped of function constants, has been defined as a basis for simple reasoning machines. mGDL allows to easily map rules to C++ functions. 253 out of 270 tested GDL rule sheets conformed to mGDL without any modifications; the rest required minor changes. A revised (m)GDL to C++ translation scheme has been reevaluated; it brought gains ranging from 28% to 7300% over YAP Prolog, managing to compile even demanding rule sheets under few seconds. For strengthening game knowledge, spatial features inspired by similar successful techniques from computer Go have been proposed. For they required an Euclidean metric, a small board extension to GDL has been defined through a set of ground atomic sentences. An SGA-based genetic algorithm has been designed for tweaking game parameters and conducting self-plays, so the features could be mined from meaningful game records. The approach has been tested on a small cluster, giving performance gains up to 20% more wins against the baseline UCT player. Implementations of proposed ideas constitutes the core of GGP Spatium - a small C++/Python GGP framework, created for developing compact GGP Players and problem solvers.