work on how to program a computer to play chess. Since then, developing game-playing programs that can compete with (and even exceed) the abilities of the human world champions has been a long-sought-after goal of the AI research community. In Shannon’s time, it would have seemed unlikely that only a scant 50 years would be needed to develop programs that play world-class backgammon, checkers, ...

This paper reports a preliminary research of application of inductive logic programming for pruning nodes in the alpha-beta gametree search method, which nds an appropriate move by looking game-trees in a limited depth ahead. The alpha-beta method reduces the number of nodes by keeping and updating lower and upper bounds of static evaluation. Pruning e ect depends on an accidental order of node...

In this paper we show how abstractions can help UCT’s performance. Ideal abstractions are homomorphisms because they preserve optimal policies, but they rarely exist, and are computationally hard to find even when they do. We show how a combination of (i) finding local abstractions in the layered-DAG MDP induced by a set of UCT trajectories (rather than finding abstractions in the global MDP), ...

We compare Temporal Difference Learning (TDL) with Coevolutionary Learning (CEL) on Othello. Apart from using three popular single-criteria performance measures: i) generalization performance or expected utility, ii) average results against a hand-crafted heuristic and iii) result in a head to head match, we compare the algorithms using performance profiles. This multi-criteria performance meas...

Decision-theoretic control of search has previously used as its basic unit of com­ putation the generation and evaluation of a complete set of successors. Although this simplifies analysis. it results in some lost opportunities for pruning and satisficing. This paper therefore extends the analysis of the value of computation to cover in­ dividual successor evaluations. The ana­ lytic techniques...

Perfect knowledge about a domain renders search unnecessary and, likewise, exhaustive search obviates heuristic knowledge. In practise, a tradeoff is found somewhere in the middle, since neither extreme is feasible for interesting domains. During the last two decades, the focus for increasing the performance of two-player game-playing programs has been on enhanced search, usually by faster hard...

In Opponent-Model search (OM search) perfect knowledge of the opponent's evaluation function is assumed. This knowledge may lead to the conclusion that the opponent intends to make an error in a given position. As a consequence the error may be exploited to the advantage of the player possessing the knowledge. In such an OM-search model, it is implicitly assumed that both players search to the ...