Coevolution of a Backgammon Player
Coevolution of a Backgammon Player
J. Pollack,A. Blair
1996
136 Citations
TLDR
The results show co-evolution to be a powerful machine learning method, even when coupled with simple hillclimbing, and suggest that the surprising success of Tesauro’s program had more to do with the co-Evolutionary structure of the learning task and the dynamics of the backgammon game itself, than to sophistication in the learning techniques.
