ABSTRACT
Scientists have often wondered how baseball outfielders can judge a fly ball by running either forward or backward and arriving at the right point at the right time to catch the ball before it hits the ground [4, 5, 9]. Such a trajectory interception problem is most difficult when the fielder is in the plane of the ball’s motion. In this case the fielder does not have a perspective view of the ball’s trajectory (Figure 1). Yet, moments after the batter hits the ball, the fielder has to decide if it is a short pop up in front, or a high fly ball over the fielder’s head, and run accordingly. Thus, there is an important temporal credit assignment problem in judging a fly ball, since the success or failure signal is obtained long after the actions that lead to that signal are taken. Considerable work in experimental psychology has focused on identifying the perceptual features that a fielder uses to judge a fly ball [8, 9]. Several alternative hypothesis, as to what perceptual features are important in making the decisions, have been postulated. In this paper, we explore the problem in detail using reinforcement learning models. Our experimental results show that one prime hypothesis made earlier about the necessary perceptual features is not sufficiently strong enough to learn the task using reinforcement learning models. We also investigate other perceptual features that help in learning this task. We believe that trying to solve such tasks using reinforcement learning models can provide us with clues that can better guide future research in experimental psychology. The task of the fielder is to run and intercept the ball at the end of the ball's trajectory. https://s3-euw1-ap-pe-df-pch-content-public-p.s3.eu-west-1.amazonaws.com/9781315784076/744dcdac-ef6b-4709-bdaa-84955f763c9b/content/fig6_1.tif"/>
