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

Cazenave, Tristan; Liu, Jialin; Teytaud, Fabien; Teytaud, Olivier

Cazenave, Tristan; Liu, Jialin; Teytaud, Fabien; Teytaud, Olivier (2016), Learning opening books in partially observable games: using random seeds in Phantom Go, IEEE CIG 2016 - Computer intelligence and Games, 2016-09, Santorini, Greece

Type

Communication / Conférence

External document link

https://hal.inria.fr/hal-01413229

Date

2016

Conference title

IEEE CIG 2016 - Computer intelligence and Games

Conference date

2016-09

Conference city

Santorini

Conference country

Greece

Metadata

Show full item record

Author(s)

Cazenave, Tristan
Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Liu, Jialin

Teytaud, Fabien

Teytaud, Olivier

Abstract (EN)

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.

Subjects / Keywords

Phantom Go