Zero-Sum Games between Large-Population Teams: Reachability-based Analysis under Mean-Field Sharing
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.
Code (1)
Similar Papers 제목 키워드 기반
Team-PSRO for Learning Approximate TMECor in Large Team Games via Cooperative Reinforcement Learning
Recent algorithms have achieved superhuman performance at a number of two-player zero-sum games such as poker and go. However, many real-world situations are multi-player games. Zero-sum two-team games, such as bridge an…
Mean field teams and games with correlated types
Mean field games have traditionally been defined~[1,2] as a model of large scale interaction of players where each player has a private type that is independent across the players. In this paper, we introduce a new model…
Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games
The predominant paradigm in evolutionary game theory and more generally online learning in games is based on a clear distinction between a population of dynamic agents that interact given a fixed, static game. In this pa…
MF-OML: Online Mean-Field Reinforcement Learning with Occupation Measures for Large Population Games
Reinforcement learning for multi-agent games has attracted lots of attention recently. However, given the challenge of solving Nash equilibria for large population games, existing works with guaranteed polynomial complex…
Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningGlobal Policy-Space Response Oracles for Two-Player Zero-Sum Games
The Policy-Space Response Oracles (PSRO) framework scales equilibrium computation to large zero-sum games by iteratively expanding a restricted strategy set using deep reinforcement learning (DRL). A central challenge is…
Reinforcement Learning