Quick and Accurate Affordance Learning

TL;DR

This paper presents a deep learning model that actively explores environments to learn affordances, emphasizing the importance of uncertainty measures and navigation strategies for efficient learning, inspired by infant behavior.

Contribution

The study introduces a novel deep learning architecture that combines global exploration with local affordance learning, utilizing Jensen-Shannon Divergence for balanced active exploration.

Findings

JSD provides the most balanced exploration strategy.

Model effectively distinguishes epistemic from aleatoric uncertainty.

Active navigation enhances affordance learning efficiency.

Abstract

Infants learn actively in their environments, shaping their own learning curricula. They learn about their environments' affordances, that is, how local circumstances determine how their behavior can affect the environment. Here we model this type of behavior by means of a deep learning architecture. The architecture mediates between global cognitive map exploration and local affordance learning. Inference processes actively move the simulated agent towards regions where they expect affordance-related knowledge gain. We contrast three measures of uncertainty to guide this exploration: predicted uncertainty of a model, standard deviation between the means of several models (SD), and the Jensen-Shannon Divergence (JSD) between several models. We show that the first measure gets fooled by aleatoric uncertainty inherent in the environment, while the two other measures focus learning on epistemic uncertainty. JSD exhibits the most balanced exploration strategy. From a computational perspective, our model suggests three key ingredients for coordinating the active generation of learning curricula: (1) Navigation behavior needs to be coordinated with local motor behavior for enabling active affordance learning. (2) Affordances need to be encoded locally for acquiring generalized knowledge. (3) Effective active affordance learning mechanisms should use density comparison techniques for estimating expected knowledge gain. Future work may seek collaborations with developmental psychology to model active play in children in more realistic scenarios.