複数の状態行動価値表を用いたR学習の高速化

抄録

We propose a method to improve the performance of R-learning, a reinforcement learning algorithm, by using multiple state-action value tables. Unlike Q- or Sarsa learning, R-learning learns a policy to maximize undiscounted rewards. Multiple state-action value tables cause substantial explorations as needed and make R-learnings to work well. Efficiency of the proposed method is verified through experiments in simulation environment.