1C1-2 複数のエージェントの経験に基づく強化学習法(1C1 強化学習)

概要

論文の詳細を見る
In general reinforcement learning algorithms, a single agent learns to achieve a goal through many episodes. If a learning problem is complicated, it may take much computation time to obtain the optimal policy. Meanwhile, for optimization problems, multi-agent search methods such as particle swarm optimization have been recognized that they are able to find rapidly a global optimal solution for multi-modal functions with wide solution space. Thus, in the previous papers we proposed a reinforcement learning algorithm in which multiple agents learn through exchanging information on respective experiences. In this algorithm, it is important how to design a method of exchanging the information. Thus, this paper proposes various methods of exchanging the information. The proposed algorithms using these methods are applied to a shortest path problem, and their performances are compared through numerical experiments.
2006-09-25