Chen, Y;
Deng, X;
Li, C;
Mguni, D;
Wang, J;
Yan, X;
Yang, Y;
(2022)
On the Convergence of Fictitious Play: A Decomposition Approach.
In:
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence 2022.
(pp. pp. 179-185).
IJCAI: International Joint Conferences on Artificial Intelligence Organization
Preview |
PDF
0026.pdf - Published Version Download (445kB) | Preview |
Abstract
Fictitious play (FP) is one of the most fundamental game-theoretical learning frameworks for computing Nash equilibrium in n-player games, which builds the foundation for modern multi-agent learning algorithms. Although FP has provable convergence guarantees on zero-sum games and potential games, many real-world problems are often a mixture of both and the convergence property of FP has not been fully studied yet. In this paper, we extend the convergence results of FP to the combinations of such games and beyond. Specifically, we derive new conditions for FP to converge by leveraging game decomposition techniques. We further develop a linear relationship unifying cooperation and competition in the sense that these two classes of games are mutually transferable. Finally, we analyze a non-convergent example of FP, the Shapley game, and develop sufficient conditions for FP to converge.
| Type: | Proceedings paper |
|---|---|
| Title: | On the Convergence of Fictitious Play: A Decomposition Approach |
| Event: | IJCAI-22 |
| Location: | Vienna, Austria |
| Dates: | 23 Jul 2022 - 29 Jul 2022 |
| ISBN-13: | 9781956792003 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.24963/ijcai.2022/26 |
| Publisher version: | https://doi.org/10.24963/ijcai.2022/26 |
| Language: | English |
| Additional information: | This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Agent-based and Multi-agent Systems: Noncooperative Games, Agent-based and Multi-agent Systems: Multi-agent Learning, Agent-based and Multi-agent Systems: Algorithmic Game Theory |
| UCL classification: | UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science UCL > Provost and Vice Provost Offices > UCL BEAMS UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10156554 |
Archive Staff Only
 |
View Item |
