Behavioral game theory seeks to describe the way actual people (as compared to idealized, rational agents) act in strategic situations. Our own recent work has identified iterative models (such as quantal cognitive hierarchy) as the state of the art for predicting human play in unrepeated, simultaneous-move games (Wright & Leyton-Brown 2012, 2016). Iterative models predict that agents reason iteratively about their opponents, building up from a specification of nonstrategic behavior called level-0. The modeler is in principle free to choose any description of level-0 behavior that makes sense for the setting. However, almost all existing work specifies this behavior as a uniform distribution over actions. In most games it is not plausible that even nonstrategic agents would choose an action uniformly at random, nor that other agents would expect them to do so. A more accurate model for level-0 behavior has the potential to dramatically improve predictions of human behavior, since a substantial fraction of agents may play level-0 strategies directly, and furthermore since iterative models ground all higher-level strategies in responses to the level-0 strategy. Our work considers models of the way in which level-0 agents construct a probability distribution over actions, given an arbitrary game. Using a Bayesian optimization package called SMAC (Hutter, Hoos, & Leyton-Brown, 2010, 2011, 2012), we systematically evaluated a large space of such models, each of which makes its prediction based only on general features that can be computed from any normal form game. In the end, we recommend a model that achieved excellent performance across the board: a linear weighting of features that requires the estimation of four weights. We evaluated the effects of combining this new level-0 model with several iterative models, and observed large improvements in the models predictive accuracies.
تحميل البحث