抄録
This paper proposes a behavioral strategy called expectation of cooperation strategy with which cooperation in the prisoner's dilemma game emerges in agent networks by incorporating Q-learning. The proposed strategy is simple and easy to implement but nevertheless can evolve and maintain cooperation in all agent networks under certain conditions. We conducted a number of experiments to clarify these conditions, and the results indicate that cooperation emerged.
| 本文言語 | English |
|---|---|
| ホスト出版物のタイトル | AAMAS 2016 - Proceedings of the 2016 International Conference on Autonomous Agents and Multiagent Systems |
| 出版社 | International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS) |
| ページ | 1333-1334 |
| ページ数 | 2 |
| ISBN（電子版） | 9781450342391 |
| 出版ステータス | Published - 2016 |
| イベント | 15th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2016 - Singapore, Singapore 継続期間: 2016 5 9 → 2016 5 13 |
Other
| Other | 15th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2016 |
|---|---|
| 国/地域 | Singapore |
| City | Singapore |
| Period | 16/5/9 → 16/5/13 |
ASJC Scopus subject areas
- 人工知能
- ソフトウェア
- 制御およびシステム工学