论文标题
定期策略II：概括和扩展
Periodic Strategies II: Generalizations and Extensions
论文作者
论文摘要
在混合的纳什均衡状态下，只要对手坚持自己的动作，球员的回报就不取决于她自己的行动。在定期策略中，相比之下，先前论文中提出的概念（Arxiv：1307.2035v4）并不取决于对手的行动。在这里，我们将其推广到多玩家同时完美的信息策略形式游戏。我们表明，在这类游戏中，总是至少存在一种定期策略，我们研究了这种周期性策略的数学属性。此外，我们证明了具有不完整信息的游戏中可能存在定期策略。我们将专注于贝叶斯游戏。此外，我们讨论了周期性策略形式主义与合作游戏理论之间的差异。实际上，定期策略是以纯粹的非合作方式获得的，周期性的策略与纳什均衡一样合作。最后，我们将定期策略纳入认知游戏理论框架中，并讨论这种方法的几个特征。
At a mixed Nash equilibrium, the payoff of a player does not depend on her own action, as long as her opponent sticks to his. In a periodic strategy, a concept developed in a previous paper (arXiv:1307.2035v4), in contrast, the own payoff does not depend on the opponent's action. Here, we generalize this to multi-player simultaneous perfect information strategic form games. We show that also in this class of games, there always exists at least one periodic strategy, and we investigate the mathematical properties of such periodic strategies. In addition, we demonstrate that periodic strategies may exist in games with incomplete information; we shall focus on Bayesian games. Moreover we discuss the differences between the periodic strategies formalism and cooperative game theory. In fact, the periodic strategies are obtained in a purely non-cooperative way, and periodic strategies are as cooperative as the Nash equilibria are. Finally, we incorporate the periodic strategies in an epistemic game theory framework, and discuss several features of this approach.
