Home // International Journal On Advances in Intelligent Systems, volume 10, numbers 1 and 2, 2017 // View article

Learning Method by Sharing Activity Histories in Multiagent Environment

Authors:
Keinosuke Matsumoto
Takuya Gohara
Naoki Mori

Keywords: machine learning; Q-learning; sharing of activity histories; agents; hunter game

Abstract:
Applications of multiagent systems are expected for parallel and distributed processing. Reinforcement learning is　used as an implementation method for learning the actions of the agent. However, when systems must control many agents, the speed of learning becomes slower. Hence, Modular Q-Learning is proposed to solve this problem. Given that it deals with partial states, the number of states is reduced to avoid exponential increases. However, if

Pages: 71 to 80

Copyright: Copyright (c) to authors, 2017. Used with permission.

Publication date: June 30, 2017

Published in: journal

ISSN: 1942-2679