Operations research and management science are often confronted with sequential decision making problems with large state spaces. Standard methods that are used for solving such complex problems are associated with some difficulties. As we discuss in this article, these methods are plagued by the so-called curse of dimensionality and the curse of modelling. In this article, we discuss reinforce...

The purpose of reinforcement learning system is to learn optimal policies in general. However, from the engineering point of view, it is useful and important to acquire not only optimal policies, but also penalty avoiding policies. In this paper, we are focused on formation of penalty avoiding policies based on the Penalty Avoiding Rational Policy Making algorithm [1]. In applying the algorithm...

The machine learning algorithm of [3] is applied to the problem of learning which heuristics to apply when playing the board game Othello. The problem is large, for there are 46,875 heuristics considered. The results are respectable; the Learner is able to beat a practiced human player approximately fifty percent of the time. Suggestions for improvement are included.

A constant dilemma facing game-playing programs is whether to emphasize searching or knowledge. This paper describes a world-championship level Othello program, BILL, that succeeds in both dimensions. The success of BILL is largely due to its understanding of many important Othello features by using a pre-compiled knowledge base of board patterns. Because of this pre-compiled nature of its know...

Monte-Carlo Tree Search (MCTS) has been found to play suboptimally in some tactical domains due to its highly selective search, focusing only on the most promising moves. In order to combine the strategic strength of MCTS and the tactical strength of minimax, MCTSminimax hybrids have been introduced, embedding shallow minimax searches into the MCTS framework. Their results have been promising e...