A Hierarchical Reinforcement Learning Algorithm Based On Heuristic Reward Function

A hierarchical reinforcement learning method based on heuristic reward function is proposed to solve the problem of "curse of dimensionality", that is the states space will grow exponentially in the number of features, and low convergence speed. The method can reduce state spaces greatly and can enhance the speed of the study. Choose actions with favorable purpose and efficiency so as to optimize reward function and enhance convergence speed. Apply this method to the Tetris game; the experiment result shows that the method can partly solve the "curse of dimensionality" and can enhance the convergence speed prominent.