Computational models of the emergence of self-exploration in 2-month-old infants

Abstract

Infants actively explore the relationship between actions and their associated effects (i.e., sensorimotor contingencies) before full-blown agency emerges. While there is experimental evidence for this development during the first year of life, the interplay of the associated cognitive processes is not yet well understood. This paper uses computational modeling to examine how exploratory behavior develops, based on one of the earliest experiments showing such behavior. In a seminal study of Rochat & Striano (1999), 2-month-old infants, contrary to newborns, showed differential behavioral patterns towards mouth-contingent sounds versus random sounds. This is interpreted as early evidence for action-effect exploration. We consider seven potential developmental factors as possibly explaining the emergence of active exploratory behavior in 2-month-olds: i) outcome prediction, ii) novelty preference, iii) fatigue, iv) strength, v) memory, vi) sensory noise, and vii) motor noise. These factors were implemented in both a supervised-learning model and a reinforcement learning model. Results from both models indicate that increased memory capacity with age is a key developmental factor underlying active exploration and, possibly, agency. Our code is published at: https://github.com/SpisakJ/Computational-models-of-the-emergence-of-self-exploration-in-2-month-old-infants.