The game of poker has been identified as a beneficial domain for current AI research
because of the properties it possesses such as the need to deal with hidden information and …

The second edition of this bestseller provides a practical and accessible introduction to the
main concepts, foundation, and applications of Bayesian networks. This edition contains a …

A new paradigm for search, based on Monte-Carlo simulation, has revolutionised the
performance of computer Go programs. In this article we describe two extensions to the …

Poker is an interesting test-bed for artificial intelligence research. It is a game of imperfect
information, where multiple competing agents must deal with probabilistic knowledge, risk …

Abstract Domain knowledge is crucial for effective performance in autonomous control
systems. Typically, human effort is required to encode this knowledge into a control …

We consider the problem of tactical assault planning in real-time strategy games where a
team of friendly agents must launch an assault on an enemy. This problem offers many …

This thesis studies the use of Monte-Carlo simulations for tree-search problems. The Monte-
Carlo technique we investigate is Monte-Carlo Tree Search (MCTS). It is a best-first search …

Mgnte Carlo simulations have been successfully used in classic turn-based games such as
backgammon, bridge, poker, and Scrabble. In this thesis, we apply the ideas to the problem …

In this paper we introduce the first algorithms for efficiently learning a simulation policy for
Monte-Carlo search. Our main idea is to optimise the balance of a simulation policy, so that …

Games provide competitive, dynamic environments that make ideal test beds for
computational intelligence theories, architectures, and algorithms. Natural evolution can be …