A Continuous Information Gain Measure to Find the Most Discriminatory Problems for AI Benchmarking

This paper introduces an information-theoretic method for selecting a small subset of problems which gives us the most information about a group of problem-solving algorithms. This method was tested on the games in the General Video Game AI (GVGAI) framework, allowing us to identify a smaller set of games that still gives a large amount of information about the game-playing agents. This approach can be used to make agent testing more efficient in the future. We can achieve almost as good discriminatory accuracy when testing on only a handful of games as when testing on more than a hundred games, something which is often computationally infeasible. Furthermore, this method can be extended to study the dimensions of effective variance in game design between these games, allowing us to identify which games differentiate between agents in the most complementary ways. As a side effect of this investigation, we provide an up-to-date comparison on agent performance for all GVGAI games, and an analysis of correlations between scores and win-rates across both games and agents.