A Soft Inducement Framework for Incentive-Aided Steering of No-Regret Players
This addresses incentive design in multi-agent systems for applications like economics or AI coordination, but it is incremental as it builds on existing game theory frameworks.
The paper tackles the problem of steering players in a mediator-augmented game to a desired action profile, showing that information design alone is insufficient and deriving a lower bound on required payments. It introduces a one-shot information design approach that improves convergence rates by a constant factor, supported by theoretical and empirical results.
In this work, we investigate a steering problem in a mediator-augmented two-player normal-form game, where the mediator aims to guide players toward a specific action profile through information and incentive design. We first characterize the games for which successful steering is possible. Moreover, we establish that steering players to any desired action profile is not always achievable with information design alone, nor when accompanied with sublinear payment schemes. Consequently, we derive a lower bound on the constant payments required per round to achieve this goal. To address these limitations incurred with information design, we introduce an augmented approach that involves a one-shot information design phase before the start of the repeated game, transforming the prior interaction into a Stackelberg game. Finally, we theoretically demonstrate that this approach improves the convergence rate of players' action profiles to the target point by a constant factor with high probability, and support it with empirical results.