Back to Search
Start Over
Zero-Sum Games between Large-Population Teams: Reachability-based Analysis under Mean-Field Sharing
- Source :
- The 38th Annual AAAI Conference on Artificial Intelligence 2024
- Publication Year :
- 2023
-
Abstract
- This work studies the behaviors of two large-population teams competing in a discrete environment. The team-level interactions are modeled as a zero-sum game while the agent dynamics within each team is formulated as a collaborative mean-field team problem. Drawing inspiration from the mean-field literature, we first approximate the large-population team game with its infinite-population limit. Subsequently, we construct a fictitious centralized system and transform the infinite-population game to an equivalent zero-sum game between two coordinators. We study the optimal coordination strategies for each team via a novel reachability analysis and later translate them back to decentralized strategies that the original agents deploy. We prove that the strategies are $\epsilon$-optimal for the original finite-population team game, and we further show that the suboptimality diminishes when team size approaches infinity. The theoretical guarantees are verified by numerical examples.<br />Comment: Published in AAAI 2024
- Subjects :
- Electrical Engineering and Systems Science - Systems and Control
Subjects
Details
- Database :
- arXiv
- Journal :
- The 38th Annual AAAI Conference on Artificial Intelligence 2024
- Publication Type :
- Report
- Accession number :
- edsarx.2303.12243
- Document Type :
- Working Paper