General Video Game Evaluation Using Relative Algorithm Performance Profiles

Thorbjørn S. Nielsen, Gabriella A. B. Barros, Julian Togelius, Mark J. Nelson

Abstract: In order to generate complete games through evolution we need generic and reliably evaluation functions for games. It has been suggested that game quality could be characterised through playing a game with different controllers and comparing their performance. This paper explores that idea through investigating the relative performance of different general game-playing algorithms. Seven game-playing algorithms was used to play several hand-designed, mutated and randomly generated VGDL game descriptions. Results discussed appear to support the conjecture that well-designed games have, in average, a higher performance difference between better and worse game-playing algorithms.