Paper detail

Predicting Plans and Actions in Two-Player Repeated Games

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.