Thumbnail - Request a copy

Expert Iteration for Risk

Gnecco, Lucas; Cazenave, Tristan, Expert Iteration for Risk, Advances in Computer Games : ACG 2021, Springer International Publishing : Berlin Heidelberg, p. 27-37. 10.1007/978-3-031-11488-5_3

Type
Communication / Conférence
Conference title
Advances in Computer Games: 17th International Conference (ACG 2021)
Conference date
2021-11
Conference city
Virtual event
Conference country
France
Book title
Advances in Computer Games : ACG 2021
Publisher
Springer International Publishing
Published in
Berlin Heidelberg
ISBN
978-3-031-11487-8
Number of pages
257
Pages
27-37
Publication identifier
Metadata
Show full item record
Author(s)
Gnecco, Lucas cc
Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Cazenave, Tristan
Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Abstract (EN)
Risk is a complex strategy game that may be easier to understand for humans than chess but harder to deal with for computers. The main reasons are the stochastic nature of battles and the different decisions that must be coordinated within turns. Our goal is to create an artificial intelligence able to play the game without human knowledge using the Expert Iteration framework. We use graph neural networks to learn the policies for the different decisions and the value estimation. Experiments on a synthetic board show that with this framework the model can rapidly learn a good country drafting policy, while the main game phases remain a challenge.