An Action Selection Method Using Degree of Cooperation in a Multi-agent Reinforcement Learning System

DOI

10.2991/jrnal.2014.1.3.13How to use a DOI?

Keywords

Multi-agent system, Reinforcement leaning, Cooperative action, Dividual, Degree of cooperation

Abstract

In recent years, a concept of a dividual is proposed by a Japanese novelist to interact properly with another person. To construct a model of the dividual, the degree of cooperation is assigned to the corresponding dividual. By introducing the degree of cooperation into a multi-agent system, we evaluate what kind of changes appears in the agent behavior. In addition, we propose an action selection method by introducing the degree of cooperation into the soft-max method in a multi-agent system. Using the proposed method, we confirm whether the cooperative action is promoted or suppressed through computer simulations.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - JOUR
AU  - Masanori Kawamura
AU  - Kunikazu Kobayashi
PY  - 2014
DA  - 2014/12/15
TI  - An Action Selection Method Using Degree of Cooperation in a Multi-agent Reinforcement Learning System
JO  - Journal of Robotics, Networking and Artificial Life
SP  - 231
EP  - 236
VL  - 1
IS  - 3
SN  - 2352-6386
UR  - https://doi.org/10.2991/jrnal.2014.1.3.13
DO  - 10.2991/jrnal.2014.1.3.13
ID  - Kawamura2014
ER  -