An Action Selection Method Using Degree of Cooperation in a Multi-agent Reinforcement Learning System
- https://doi.org/10.2991/jrnal.2014.1.3.13How to use a DOI?
- Multi-agent system, Reinforcement leaning, Cooperative action, Dividual, Degree of cooperation
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.
- © 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/).
Cite this article
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 - https://doi.org/10.2991/jrnal.2014.1.3.13 ID - Kawamura2014 ER -