The creation of a complex web site is a thorny problem in user interface design. First, different visitors have distinct goals. Second, even a single visitor may have different needs at different times. Much of the information at the site may also be dynamic or time-dependent. Third, as the site grows and evolves, its original design may no longer be appropriate. Finally, a site may be designed for a particular purpose but used in unexpected ways. Web servers record data about user interactions and accumulate this data over time. We believe that AI techniques can be used to examine user access logs in order to automatically improve the site. We challenge the AI community to create adaptive web sites: sites that automatically improve their organization and presentation based on user access data. Several unrelated research projects in plan recognition, machine learning, knowledge representation, and user modeling have begun to explore aspects of this problem. We hope that posing this cha...

The checkers program Chinook has won the right to play a 40-game match for the World Checkers Championship against Dr. Marion Tinsley. This was earned by placing second, after Dr. Tinsley, at the 1990 U.S. National Open, the biennial event used to determine a challenger for the Championship. This is the first time a program has earned the right to contest for a human World Championship. In an exhibition match played in December 1990, Tinsley narrowly defeated Chinook 7.5 - 6.5. This paper describes the program, the research problems encountered and our solutions. Many of the techniques used for computer chess are directly applicable to computer checkers. However, the problems of building a world championship caliber program force us to address some issues that have, to date, been largely ignored by the computer chess community.

Many enhancements to the alpha-beta algorithm have been proposed to help reduce the size of minimax trees. A recent enhancement, the history heuristic, is described that improves the order in which branches are considered at interior nodes. A comprehensive set of experiments is reported which tries all combinations of enhancements to determine which one yields the best performance. Previous work on assessing their performance has concentrated on the benefits of individual enhancements or a few combinations. However, each enhancement should not be taken in isolation; one would like to find the combination that provides the greatest reduction in tree size. Results indicate that the history heuristic and transposition tables significantly out-perform other alpha-beta enhancements in application generated game trees. For trees up to depth 8, when taken together, they account for over 99% of the possible reductions in tree size, with the other enhancements yielding insignificant gains. Inde...

Since the beginning of AI, mind games have been studied as relevant application fields. Nowadays, some programs are better than human players in most classical games. Their results highlight the efficiency of AI methods that are now quite standard. Such methods are very useful to Go programs, but they do not enable a strong Go program to be built. The problems related to Computer Go require new AI problem solving methods. Given the great number of problems and the diversity of possible solutions, Computer Go is an attractive research domain for AI. Prospective methods of programming the game of Go will probably be of interest in other domains as well. The goal of this paper is to present Computer Go by showing the links between existing studies on Computer Go and different AI related domains: evaluation function, heuristic search, machine learning, automatic knowledge generation, mathematical morphology and cognitive science. In addition, this paper describes both the practical aspects of Go programming, such as program optimization, and various theoretical aspects such as combinatorial game theory, mathematical morphology, and MonteCarlo methods. B. Bouzy T. Cazenave page 2 08/06/01 1.

The creation of a complex web site is a thorny problem in. user interface design. In IJCAI '97, we challenged the AI community to address this problem by creating adaptive web sites. In response, we investigate the problem of index page synthesis — the automatic creation of pages that facilitate a visitor's navigation of a Web site. Previous work has employed statistical methods to generate candidate index pages that are of limited value because they do not correspond to concepts or topics that are intuitive to people. In this paper we formalize index page synthesis as a conceptual clustering problem and introduce a novel approach which we call conceptual cluster mining: we search for a small number of cohesive clusters that correspond to concepts in a given concept description language L. Next, we present SGML, an algorithm schema that combines a statistical clustering algorithm with a concept learning algorithm. The clustering algorithm is used to generate seed clusters, and the concept learning algorithm to describe these seed clusters using expressions in L. Finally, we offer preliminary experimental evidence that instantiations of SGML outperform existing algorithms (e.g., COBWEB) in this domain. 1

1 . The point of game tree search is to insulate oneself from errors in the evaluation function. The standard approach is to grow a full width tree as deep as time allows, and then value the tree as if the leaf evaluations were exact. This has been effective in many games because of the computational efficiency of the alpha-beta algorithm. Our approach is to form a Bayesian model of our uncertainty. We adopt an evaluation function that returns a probability distribution estimating the probability of various errors in valuing each position. These estimates are obtained by training from data. We thus use additional information at each leaf not available to the standard approach. We utilize this information in three ways: to evaluate which move is best after we are done expanding, to allocate additional thinking time to moves where additional time is most relevant to game outcome, and, perhaps most importantly, to expand the tree along the most relevant lines. Our measure of the relevan...

This article presents a new, game-independent selective extension of the fffi algorithm. Based on the strong correlation of evaluations obtained from searches at different depths it is shown how the result of a shallow search can be used to decide with a prescribed likelihood whether a deep search would yield a value outside the current search window. In its application to Othello, the technique is shown to be effective in investigating the relevant variations more deeply. It significantly increased the playing strength of an already strong brute--force Othello program. 1. Introduction Human players tell us that a game tree does not have to be searched in its full width in order to find a good move. Using their experience, they are able to prune in advance unpromising variations. The resulting game trees are narrow and can be rather deep. By contrast, the original minimax algorithm searches the entire game tree up to a certain depth and even its efficient improvement --- the fffi algo...

Most parallel game-tree search approaches use synchronous methods, where the work is concentrated within a specific part of the tree, or at a given search depth. This article shows that asynchronous game-tree search algorithms can be as efficient as or better than synchronous methods in determining the minimax value. APHID, a new asynchronous parallel game-tree search algorithm, is presented. APHID is implemented as a freely-available portable library, making the algorithm easy to integrate into a sequential game-tree searching program. APHID has been added to four programs written by different authors. APHID yields better speedups than synchronous search methods for an Othello and a checkers program, and comparable speedups on two chess programs.

Chinook is the strongest 8 x 8 checkers program around today. Its strength is largely a result of brute-force methods. The program is capable of searching to depths that make it a feared tactician. As with chess, knowledge is the Achilles' heel of the program. However, unlike the chess example, endgame databases go a long way to overcoming this limitation. The program has precomputed databases that classify all positions with 6 or less pieces on the board as won, lost or drawn (with 7 pieces under construction). The program came second to the human World Champion in the U.S. National Open, winning the right to play a World Championship match against him. Chinook is the first computer program in history to earn the right to play for a human World Championship.

Abstract not found