Temporal Difference Learning of Backgammon Strategy

This paper presents a case study in which the TD(A) algorithm for training connectionist networks, proposed in (Sutton, 1988), is applied to learning the game of backgammon from the outcome of self-play. This is apparently the first application of this algorithm to a complex nontrivial task. It is found that, with zero knowledge built in, networks are able to learn from scratch to play the entire game at a fairly strong intermediate level of performance, which is clearly better than conventional commercial programs, and which in fact surpasses comparable networks trained on a massive human expert data set. The hidden units in these network have apparently discovered useful features, a longstanding goal of computer games research. Furthermore, when a set of handcrafted features is added to the input representation, the resulting networks reach a near-expert level of performance, and have achieved good results in tests against world-class human play.