Swarm Reinforcement Learning Method for Multi-agent Tasks
-
- YAMAWAKE Shota
- Graduate School of Science and Technology, Kyoto Institute of Technology
-
- KUROE Yasuaki
- Graduate School of Science and Technology, Kyoto Institute of Technology
-
- IIMA Hitoshi
- Graduate School of Science and Technology, Kyoto Institute of Technology
Bibliographic Information
- Other Title
-
- マルチエージェントタスクに対する群強化学習法
- マルチエージェントタスク ニ タイスル グン キョウカ ガクシュウホウ : ジレンマ モンダイ ノ カイホウ
- —Solution of Dilemma Problems—
- —ジレンマ問題の解法—
Search this article
Abstract
In this paper, we propose a swarm reinforcement learning method for dilemma problems of multi-agent tasks in which it is difficult for agents to learn cooperative actions. In the proposed method, multiple sets of the agents and the environments, which are called learning worlds, are prepared and each agent in each world learns through exchanging information with agents in all other worlds. In order to acquire the cooperative actions, we propose a method of information exchange in which the agents in all learning worlds share the state-action values which are estimated to be superior for taking cooperative actions. The proposed method is applied to the N-persons iterated prisoner's dilemma and the Tragedy of the commons that are typical dilemma problems, and its performance is evaluated by investigating the learning processes and results.
Journal
-
- Transactions of the Society of Instrument and Control Engineers
-
Transactions of the Society of Instrument and Control Engineers 49 (3), 370-377, 2013
The Society of Instrument and Control Engineers
- Tweet
Details 詳細情報について
-
- CRID
- 1390001204503481600
-
- NII Article ID
- 10031160127
-
- NII Book ID
- AN00072392
-
- ISSN
- 18838189
- 04534654
-
- NDL BIB ID
- 024574740
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed