Abstract
In this paper, we put forward Monte-Carlo Tree Search as a novel, unified framework to game AI, which doesn't require an evaluation function. In the framework, randomized explorations of the search space are used to predict the most promising game actions. We will demonstrate that Monte-Carlo Tree Search can be applied effectively to (1) classic board-games, (2) modern board-games, and (3) video games.
Original language | English |
---|---|
Pages (from-to) | 389-390 |
Number of pages | 2 |
Journal | Belgian/Netherlands Artificial Intelligence Conference |
Publication status | Published - 2008 |
Event | 20th Belgian-Dutch Conference on Artificial Intelligence, BNAIC 2008 - Enschede, Netherlands Duration: 30 Oct 2008 → 31 Oct 2008 |
Bibliographical note
Copyright:Copyright 2013 Elsevier B.V., All rights reserved.