Multiple Tree for Partially Observable Monte-Carlo Tree Search

David Auger (1)

1 TAO - Machine Learning and Optimisation

We propose an algorithm for computing approximate Nash equilibria of partially observable games using Monte-Carlo tree search based on recent bandit methods. We obtain experimental results for the game of phantom tic-tac-toe, showing that strong strategies can be efficiently computed by our algorithm.

Mots clés: Nash equilibria; partially observable games; Monte-Carlo Tree Search

Domaines: Informatique et théorie des jeux [cs.GT]

David Auger. Multiple Tree for Partially Observable Monte-Carlo Tree Search. 2011. ⟨hal-00563480v2⟩