状態予測型強化学習システム

抄録

The present paper proposes a new reinforcement learning (RL) system called a state predictor based RL system in order to solve the explosion of state space and create cooperative behaviors in multi-agent systems. The proposed system realizes a predictive function by representing both the present and the next state-action groups with ITPM which is one of incremental topology maps. The proposed system is applied to pursuit problem, and its performance is evaluated by comparing with conventional RL method through computer simulations. The experimental result shows that the proposed system can appropriately learn in a complex environment which is hardly solved by conventional RL. Furthermore, it is confirmed that the proposed system can acquire cooperative strategies.