Improving Temporal Difference Learning Performance in Backgammon Variants

Palamedes is an ongoing project for building expert playing bots that can play backgammon variants. As in all successful modern backgammon programs, it is based on neural networks trained using temporal difference learning. This paper improves upon the training method that we used in our previous approach for the two backgammon variants popular in Greece and neighboring countries, Plakoto and Fevga. We show that the proposed methods result both in faster learning as well as better performance. We also present insights about the selection of the features in our experiments that can be useful to temporal difference learning in other games as well.