Skip to Main content Skip to Navigation
Conference papers

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.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/hal-01413229
Contributor : Fabien Teytaud <>
Submitted on : Friday, December 9, 2016 - 3:08:26 PM
Last modification on : Thursday, January 21, 2021 - 10:54:02 PM
Long-term archiving on: : Thursday, March 23, 2017 - 10:22:09 AM

File

seedPhantomGo.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01413229, version 1

Citation

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⟩

Share

Metrics

Record views

510

Files downloads

223