Learning opening books in partially observable games: using random seeds in Phantom Go - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

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 5x5 against the same AI, and from approximately 0% to 40% in 5x5, 7x7 and 9x9 against a stronger (learning) opponent.
Fichier principal
Vignette du fichier
seedPhantomGo.pdf (3.2 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01413229 , version 1 (09-12-2016)

Identifiers

  • HAL Id : hal-01413229 , version 1

Cite

Tristan Cazenave, Jialin Liu, Fabien Teytaud, Olivier Teytaud. Learning opening books in partially observable games: using random seeds in Phantom Go. CIG 2016 - Computer intelligence and Games, Sep 2016, Santorini, Greece. ⟨hal-01413229⟩
322 View
136 Download

Share

Gmail Facebook X LinkedIn More