arXiv Open Access 2011

Multiple Tree for Partially Observable Monte-Carlo Tree Search

David Auger

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.GT

Penulis (1)

David Auger

Format Sitasi

APA MLA BibTeX

Auger, D. (2011). Multiple Tree for Partially Observable Monte-Carlo Tree Search. https://arxiv.org/abs/1102.1580

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2011
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓