Ya’akov Gal, Avi Pfeffer, Francesca Marzo, and Barbara J. Grosz
This paper presents a machine-learning approach to modeling human behavior in one-shot games. It provides a framework for representing and reasoning about the social factors that affect people’s play. The model predicts how a human player is likely to react to different actions of another player, and these predictions are used to determine the best possible strategy for that player. Data collection and evaluation of the model were performed on a negotiation game in which humans played against each other and against computer models playing various strategies. A computer player trained on human data outplayed Nash equilibrium and Nash bargaining computer players as well as humans. It also generalized to play people and game situations it had not seen before.