Learning, defined as changes in behavior that occur due to past experience, has been well documented for nearly 20 species of hymenopterous parasitoids. Few studies, however, have explored the influence of learning on population-level patterns of host use by parasitoids in field populations. Our study explores learning in the parasitoid Aphidius ervi Haliday that attacks pea aphids, Acyrthosiphon pisum (Harris). We used a sequence of laboratory experiments to investigate whether there is a learned component in the selection of red or green aphid color morphs. We then used the results of these experiments to parameterize a model that examines whether learned behaviors can explain the changes in the rates of parasitism observed in field populations in South-central Wisconsin, USA. In the first of two experiments, we measured the sequence of host choice by A. ervi on pea aphid color morphs and analyzed this sequence for patterns in biased host selection. Parasitoids exhibited an inherent preference for green aphid morphs, but this preference was malleable; initial encounters with red aphids led to a greater chance of subsequent orientation towards red aphids than predicted by chance. In a second experiment, we found no evidence that parasitoids specialize on red or green morphs; for the same parasitoids tested in trials separated by 2 h, color preference in the first trial did not predict color preference in the second, as would be expected if they differed in fixed preferences or exhibited long-term (> 2 h) learning. Using data from the two experiments, we parameterized a population dynamics model and found that learning of the magnitude observed in our experiments leads to biased parasitism towards the most common color morph. This bias is sufficient to explain changes in the ratio of aphid color morphs observed in field sites over multiple years. Our study suggests that for even relatively simple organisms, learned behaviors may be important for explaining the population dynamics of their hosts.