Abstract
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.
| Original language | English |
|---|---|
| Title of host publication | AAMAS 2016 - Proceedings of the 2016 International Conference on Autonomous Agents and Multiagent Systems |
| Publisher | International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS) |
| Pages | 1333-1334 |
| Number of pages | 2 |
| ISBN (Electronic) | 9781450342391 |
| Publication status | Published - 2016 |
| Event | 15th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2016 - Singapore, Singapore Duration: 2016 May 9 → 2016 May 13 |
Other
| Other | 15th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2016 |
|---|---|
| Country | Singapore |
| City | Singapore |
| Period | 16/5/9 → 16/5/13 |
Fingerprint
Keywords
- Complex networks
- Norm
- Prisoner's dilemma
ASJC Scopus subject areas
- Artificial Intelligence
- Software
- Control and Systems Engineering
Cite this
Emergence of cooperation in complex agent networks based on expectation of cooperation. / Shibusawa, Ryosuke; Otsuka, Tomoaki; Sugawara, Toshiharu.
AAMAS 2016 - Proceedings of the 2016 International Conference on Autonomous Agents and Multiagent Systems. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2016. p. 1333-1334.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Emergence of cooperation in complex agent networks based on expectation of cooperation
AU - Shibusawa, Ryosuke
AU - Otsuka, Tomoaki
AU - Sugawara, Toshiharu
PY - 2016
Y1 - 2016
N2 - 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.
AB - 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.
KW - Complex networks
KW - Norm
KW - Prisoner's dilemma
UR - http://www.scopus.com/inward/record.url?scp=85014165427&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85014165427&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85014165427
SP - 1333
EP - 1334
BT - AAMAS 2016 - Proceedings of the 2016 International Conference on Autonomous Agents and Multiagent Systems
PB - International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
ER -