It has been long recognized that different people may use different strategies, or decision rules, when playing games or dealing with other complex decision problems. We provide a new Bayesian procedure for drawing inferences about the nature and number of decision rules that are present in a population of agents who are each confronted with a dynamic decision problem. We apply our procedure to analyze the behavior of group of subjects in a laboratory setting. The procedure performs very well at grouping people into types. We were surprised to find that, in a very difficult dynamic decision problem, nearly a third of people were able to closely approximate the optimal decision rule, while more than another third were able to uncover a very good rule of thumb.