The problem of sound field reproduction (SFR) in the case where the location and parameters of the primary source are known in advance has been well studied. In this paper, we tackle the problem of SFR when there is uncertainty about the location and radiation pattern of the primary source. To account for various possibilities, we sample from the collection of the likely locations and source parameters, and learn a dictionary that is able to provide a good representation of this class of sound fields. We then design loudspeaker radiation patterns to approximate the learned dictionary. Simulations show that the proposed approach offers better performance to the previously known SFR methods in cases where the location and radiation pattern of the primary source is unknown. The formulation is 2D in free space, with directional loudspeakers and pressure sampling points that correspond to omni microphones.