# Emergence of Structured Behaviors from Curiosity-Based Intrinsic Motivation

## TL;DR

This paper demonstrates that curiosity-driven intrinsic motivation in neural networks can lead to the emergence of complex, structured behaviors and improved understanding of object dynamics in a naturalistic environment.

## Contribution

It introduces a neural network model that uses curiosity-based intrinsic motivation to develop structured behaviors and enhance object understanding without extrinsic rewards.

## Key findings

- Emergence of ego motion prediction, object attention, and gathering behaviors
- Improved performance on object dynamics prediction and localization
- Proof-of-principle for intrinsic motivation models in developmental learning

## Abstract

Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to replicate some of these abilities with a neural network that implements curiosity-driven intrinsic motivation. Using a simple but ecologically naturalistic simulated environment in which the agent can move and interact with objects it sees, the agent learns a world model predicting the dynamic consequences of its actions. Simultaneously, the agent learns to take actions that adversarially challenge the developing world model, pushing the agent to explore novel and informative interactions with its environment. We demonstrate that this policy leads to the self-supervised emergence of a spectrum of complex behaviors, including ego motion prediction, object attention, and object gathering. Moreover, the world model that the agent learns supports improved performance on object dynamics prediction and localization tasks. Our results are a proof-of-principle that computational models of intrinsic motivation might account for key features of developmental visuomotor learning in infants.