Nash equilibrium is often heralded as a guiding principle for rational decision-making in strategic interactions. However, it is well-known that Nash equilibrium sometimes fails as a reliable predictor of outcomes, with two of the most notable issues being the fact that it is not resilient to collusion and that there may be multiple Nash equilibria in a single game. In this paper, we show that a mechanism designer can get around these two issues for free by expanding the action sets of the original game. More precisely, given a normal-form or Bayesian game $\Gamma$ and a Nash equilibrium $\vec{\sigma}$ in $\Gamma$, a mechanism designer can construct a new game $\Gamma^{\vec{\sigma}}$ by expanding the action set of each player and defining appropriate utilities in the action profiles that were not already in the original game. We show that the designer can construct $\Gamma^{\vec{\sigma}}$ in such a way that (a) $\vec{\sigma}$ is a semi-strong Nash equilibrium of $\Gamma^{\vec{\sigma}}$, and (b) $\vec{\sigma}$ Pareto-dominates or quasi Pareto-dominates all other Nash equilibria of $\Gamma^{\vec{\sigma}}$.
翻译:暂无翻译