Gabriella A. B. Barros

General Video Game Evaluation Using Relative Algorithm Performance Profiles

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.

Towards generating arcade game rules with VGDL

We describe an attempt to generate complete arcade games using the Video Game Description Language (VGDL) and the General Video Game Playing environment (GVG-AI). Games are generated by an evolutionary algorithm working on genotypes represented as VGDL descriptions. In order to direct evolution towards good games, we need an evaluation function that accurately estimates game quality. The evaluation function used here is based on the differential performance of several game-playing algorithms, or Relative Algorithm Performance Profiles (RAPP): it is assumed that good games allow good players to play better than bad players. For the purpose of such evaluations, we introduce two new game tree search algorithms, DeepSearch and Explorer; these perform very well on benchmark games and constitute a substantial subsidiary contribution of the paper. In the end, the attempt to generate arcade games is only partially successful, as some of the games have interesting design features but are barely playable as generated. An analysis of these shortcomings yields several suggestions to guide future attempts at arcade game generation.

Exploring a large space of small games

We explore the soundness and playability of randomly generated games expressed in the Video Game Description Language (VGDL). A grammar is defined for VGDL, which is able to express a large variety of simple arcade-like games, and random expansions of this grammar are fed to a VGDL interpreter and played with off the shelf agents. We see this work as the first step towards generating complete, playable games.