Skip to yearly menu bar Skip to main content

Workshop: Intrinsically Motivated Open-ended Learning (IMOL) Workshop

Intrinsically Motivated Social Play in Virtual Infants

Chris Doyle · Sarah Shader · Michelle Lau · Megumi Sano · Dan Yamins · Nick Haber

Keywords: [ curiosity ] [ contingent interaction ] [ Reinforcement Learning ] [ development ] [ social behavior ] [ play ] [ intrinsic motivation ]


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. 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. Our findings provide insight into how curiosity-like intrinsic rewards and contingent social interaction lead to social behavior and the creation of a robust predictive world model.

Chat is not available.