论文标题
预测两人重复游戏中的计划和行动
Predicting Plans and Actions in Two-Player Repeated Games
论文作者
论文摘要
人工智能（AI）代理人将需要与其他AI代理和人类互动。创建员工的模型有助于预测建模的代理人的行动，计划和意图。这项工作介绍了算法，可以预测重复游戏中的动作，计划和意图，并提供算法的探索。我们形成了一种生成的贝叶斯方法来模型S＃。 S＃被设计为一种强大的算法，该算法学会了在2 x 2个矩阵游戏中与其同事合作。与每个S＃专家相关的行动，计划和意图是从文献中确定的，相应地对S＃专家分组，从而根据其状态概率预测了行动，计划和意图。针对囚犯的困境探索了两种预测方法：最大后验（地图）和一种聚合方法。 MAP（〜89％的精度）表现出最适合行动预测的方法。两种方法都以〜88％的精度预测了S＃的计划。配对的t检验表明，在不廉价谈话的情况下预测S＃的动作时，地图的性能明显优于汇总。根据S＃专家的目标探索意图；结果表明，在建模S＃时准确预测目标。获得的结果表明，拟议的贝叶斯方法非常适合在两人重复比赛中对代理进行建模。
Artificial intelligence (AI) agents will need to interact with both other AI agents and humans. Creating models of associates help to predict the modeled agents' actions, plans, and intentions. This work introduces algorithms that predict actions, plans and intentions in repeated play games, with providing an exploration of algorithms. We form a generative Bayesian approach to model S#. S# is designed as a robust algorithm that learns to cooperate with its associate in 2 by 2 matrix games. The actions, plans and intentions associated with each S# expert are identified from the literature, grouping the S# experts accordingly, and thus predicting actions, plans, and intentions based on their state probabilities. Two prediction methods are explored for Prisoners Dilemma: the Maximum A Posteriori (MAP) and an Aggregation approach. MAP (~89% accuracy) performed the best for action prediction. Both methods predicted plans of S# with ~88% accuracy. Paired T-test shows that MAP performs significantly better than Aggregation for predicting S#'s actions without cheap talk. Intention is explored based on the goals of the S# experts; results show that goals are predicted precisely when modeling S#. The obtained results show that the proposed Bayesian approach is well suited for modeling agents in two-player repeated games.
