Volume 2, Issue 1, June 2015, Pages 40 - 45
Reinforcement Learning with Symbiotic Relationships for Multiagent Environments
Authors
Shingo Mabu, Masanao Obayashi, Takashi Kuremoto
Corresponding Author
Shingo Mabu
Available Online 1 June 2015.
- DOI
- 10.2991/jrnal.2015.2.1.10How to use a DOI?
- Keywords
- reinforcement learning, symbiosis, multiagent system, cooperative behavior
- Abstract
Multiagent systems, where many agents work together to achieve their objectives, and cooperative behaviors between agents need to be realized, have been widely studied In this paper, a new reinforcement learning framework considering the concept of “Symbiosis” in order to represent complicated relationships between agents and analyze the emerging behavior is proposed. In addition, distributed state-action value tables are designed to efficiently solve the multiagent problems with large number of state-action pairs. From the simulation results, it is clarified that the proposed method shows better performance comparing to the conventional reinforcement learning without considering symbiosis.
- 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/).
Cite this article
TY - JOUR AU - Shingo Mabu AU - Masanao Obayashi AU - Takashi Kuremoto PY - 2015 DA - 2015/06/01 TI - Reinforcement Learning with Symbiotic Relationships for Multiagent Environments JO - Journal of Robotics, Networking and Artificial Life SP - 40 EP - 45 VL - 2 IS - 1 SN - 2352-6386 UR - https://doi.org/10.2991/jrnal.2015.2.1.10 DO - 10.2991/jrnal.2015.2.1.10 ID - Mabu2015 ER -