Learning opening books in partially observable games: Using random seeds in Phantom Go

Abstract

Many artificial intelligences (AIs) are randomized. One can be lucky or unlucky with the random seed; we quantify this effect and show that, maybe contrarily to intuition, this is far from being negligible. Then, we apply two different existing algorithms for selecting good seeds and good probability distributions over seeds. This mainly leads to learning an opening book. We apply this to Phantom Go, which, as all phantom games, is hard for opening book learning. We improve the winning rate from 50% to 70% in 5×5 against the same AI, and from approximately 0% to 40% in 5×5, 7×7 and 9×9 against a stronger (learning) opponent.