Behavioral considerations suggest an average reward TD model of the dopamine system

Abstract

Recently there has been much interest in modeling the activity of primate midbrain dopamine neurons as signalling reward prediction error. But since the models are based on temporal-difference (TD) learning, they assume an exponential decline with time in the value of delayed reinforcers, an assumption long known to conflict with animal behavior. We show that a variant of TD learning that tracks variations in the average reward per timestep rather than cumulative discounted reward preserves the models’ success at explaining neurophysiological data while significantly increasing their applicability to behavioral data.