Thumbnail - Request a copy

Deep Catan

Driss, Brahim; Cazenave, Tristan (2022), Deep Catan, Applications of Evolutionary Computation : EvoApplications 2022, Springer International Publishing : Berlin Heidelberg, p. 503-513. 10.1007/978-3-031-02462-7_32

Type
Communication / Conférence
Date
2022
Conference title
25th European Conference, EvoApplications 2022, Held as Part of EvoStar 2022
Conference date
2022-04
Conference city
Madrid
Conference country
Spain
Book title
Applications of Evolutionary Computation : EvoApplications 2022
Publisher
Springer International Publishing
Published in
Berlin Heidelberg
ISBN
978-3-031-02461-0
Number of pages
756
Pages
503-513
Publication identifier
Metadata
Show full item record
Author(s)
Driss, Brahim
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)
Catan is a popular multiplayer board game that involves multiple gameplay notions: stochastic elements related to the dice rolls as well as to the initial placement of resources on the map and the drawing of development cards, strategic notions for the placement of the cities and the roads which call upon topological and shape recognition notions and notions of expectation of gains linked to the probabilities of the rolls of the dice. In this paper, we develop a policy for this game using a convolutional neural network. The used deep reinforcement learning algorithm is Expert Iteration which has already given excellent results for Alpha Zero and its descendants.
Subjects / Keywords
Multiplayer board game; Convolutional neural network; Deep reinforcement learning algorithm; Expert Iteration; Alpha Zero