A Proposal of Score Distribution Predictive Model in Self-Play Deep Reinforcement Learning

We propose a model for predicting the probability distribution of score in Self-Play deep reinforcement learning, which is used in game AI. In the proposed model, the probability distribution of score is obtained instead of expected value of score that is commonly used. By using it directly, the performance degradation problem in score learning is solved. Evaluation experiments comparing the proposed model with existing models show that the performance degradation problem is solved. Furthermore, the proposed model allowed more precise manipulation of score.