Developmental Curiosity and Social Interaction in Virtual Agents

TL;DR

This study explores how intrinsic motivations like curiosity and social interaction influence exploration and learning in a virtual infant agent within a 3D environment, highlighting the roles of novelty, uncertainty, and social contingencies.

Contribution

It introduces a virtual infant agent model that uses intrinsic reward functions to simulate curiosity-driven exploration and social learning in a complex environment.

Findings

Reward functions based on novelty and uncertainty promote diverse exploration.

Social contingencies enhance the agent's ability to learn predictive models.

Learning with an attentive caregiver improves understanding of complex social and physical dynamics.

Abstract

Infants explore their complex physical and social environment in an organized way. To gain insight into what intrinsic motivations may help structure this exploration, we create a virtual infant agent and place it in a developmentally-inspired 3D environment with no external rewards. The environment has a virtual caregiver agent with the capability to interact contingently with the infant agent in ways that resemble play. We test intrinsic reward functions that are similar to motivations that have been proposed to drive exploration in humans: surprise, uncertainty, novelty, and learning progress. These generic reward functions lead the infant agent to explore its environment and discover the contingencies that are embedded into the caregiver agent. The reward functions that are proxies for novelty and uncertainty are the most successful in generating diverse experiences and activating the environment contingencies. We also find that learning a world model in the presence of an attentive caregiver helps the infant agent learn how to predict scenarios with challenging social and physical dynamics. Taken together, our findings provide insight into how curiosity-like intrinsic rewards and contingent social interaction lead to dynamic social behavior and the creation of a robust predictive world model.