What do games tell us about intelligence?


The use of competitive gameplay to study artificial intelligence dates to the early days of modern AI, when Arthur Samuel developed a Checkers program in 1956 that trained itself using reinforcement learning. As computer Checkers advanced, so did Backgammon: in 1979 Hans Berliner's BKG 9.8 program defeated reigning Backgammon world champion Luigi Villa, winning the matchup 7–1. As a result, if the world's top ranked player Magnus Carlsen (Elo rating: 2851) played the 100th ranked player Loek Van Wely (Elo rating: 2653) tomorrow in a game, a large-scale analysis of historical gameplay predicts that Carlsen has about a 75% chance of beating Van Wely. In a series of excellent blog posts and research papers, computer scientist and International Master-level Chess player Ken Regan has explored the concept of a ratings horizon in Elo ratings for Chess: more and more modern computer programs mostly draw ties against each other, and Regan notes that we are steadily approaching the point where Chess programs may not lose to each other -- or to any human.

Some Studies in Machine Learning Using the Game of Checkers, II - Recent Progress


While still unable to outplay checker masters, the program's playing ability has been greatly improved. Limited progress has been made in the development of an improved book-learning technique and in the optimization of playing strategies as applied to the checker playing program described in an earlier paper with this same title.' While the investigation of the learning procedures forms the essential core of the experimental work, certain improvements have been made in playing techniques which must first be described. The way in which two limiting values (McCarthy's alpha and beta) are used in pruning can be seen by referring The move tree of Figure 1 redrawn to illustrate the detailed method used to keep track of the comparison values.