Abstract
We study the problem of achieving cooperation between two self-interested agents that play a sequence of different randomly generated normal form games. The agent learns how much the opponent is willing to cooperate and reciprocates. We present empirical results that show that both agents benefit from cooperation and that a small number of games is sufficient to learn the cooperation level of the opponent.
Original language | English (US) |
---|---|
Pages | 1185-1186 |
Number of pages | 2 |
State | Published - 2011 |
Event | 10th International Conference on Autonomous Agents and Multiagent Systems 2011, AAMAS 2011 - Taipei, Taiwan, Province of China Duration: May 2 2011 → May 6 2011 |
Other
Other | 10th International Conference on Autonomous Agents and Multiagent Systems 2011, AAMAS 2011 |
---|---|
Country/Territory | Taiwan, Province of China |
City | Taipei |
Period | 5/2/11 → 5/6/11 |
Keywords
- Game theory
- Implicit Cooperation
- Multiagent Learning