generalization

Admittedly, that is a generalization, but it’s one worth making.

"One of the benefits of this approach is that we can combine policies to get the best of both worlds. For instance, a policy trained on real-world data might be able to achieve more dexterity, while a policy trained on simulation might be able to achieve more generalization," Wang says.

Her work resists generalization — Manzoor resists it, too.

However, the Prakash-proxy model trained only on color images did not show good generalization to grayscale or hue-manipulated images.

The robust generalization of the developmentally inspired model is not merely a consequence of it having been trained on both color and grayscale images; the temporal ordering of these images makes a big difference.