A Pendulum Effect of Expert Playing in Games

Abstract—When learning how to play a strategy board game, one can measure the relative effectiveness of the learned policies by assessing how often a player wins and how easily these wins are scored. Experimental evidence also shows that when one of the competing players is trained by a sophisticated tutor, performance benefits also flow to the opponent. We present comprehensive experimental evidence that the level of tutor effectiveness is best demonstrated by the improvement of the tutored players opponent; this performance change is termed the pendulum effect. Keywords—board games; reinforcement learning; neural net-works; function approximation; temporal difference learning I