# Emergence of Structured Behaviors from Curiosity-Based Intrinsic Motivation

arXiv: https://arxiv.org/abs/1802.07461 · HTML: https://mlsanity.com/paper/1802.07461/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Latent dynamics models and model-based RL, one of 11 directions in World models.
- Builds on 2 of its 17 references that are in the map.
- First posted on arXiv 21 Feb 2018.

## Placed in

- World models / [Latent dynamics models and model-based RL](https://mlsanity.com/wm/latent-dynamics-models-and-model-based-rl/)

## Builds on (most cited first, 2 of 2)

- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Reinforcement Learning with Unsupervised Auxiliary Tasks](https://mlsanity.com/paper/1611.05397/) (2016)

## Built on by (most cited first, 3 of 3)

- [Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation](https://mlsanity.com/paper/2206.11403/) (2022)
- [Efficient Skill Discovery via Regret-Aware Optimization](https://mlsanity.com/paper/2506.21044/) (2025)
- [Neuromorphic Intelligence](https://mlsanity.com/paper/2509.11940/) (2025)

## Abstract (arXiv)

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.