# Learning To Explore With Predictive World Model Via Self-Supervised Learning

arXiv: https://arxiv.org/abs/2502.13200 · HTML: https://mlsanity.com/paper/2502.13200/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Latent dynamics models and model-based RL, one of 11 directions in World models.
- Builds on 6 of its 27 references that are in the map.
- First posted on arXiv 18 Feb 2025.

## 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, 6 of 6)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Large-Scale Study of Curiosity-Driven Learning](https://mlsanity.com/paper/1808.04355/) (2018)
- [Recurrent Independent Mechanisms](https://mlsanity.com/paper/1909.10893/) (2019)
- [Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models](https://mlsanity.com/paper/1507.00814/) (2015)
- [Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning](https://mlsanity.com/paper/1703.01732/) (2017)
- [A survey on intrinsic motivation in reinforcement learning](https://mlsanity.com/paper/1908.06976/) (2019)

## Abstract (arXiv)

Autonomous artificial agents must be able to learn behaviors in complex environments without humans to design tasks and rewards. Designing these functions for each environment is not feasible, thus, motivating the development of intrinsic reward functions. In this paper, we propose using several cognitive elements that have been neglected for a long time to build an internal world model for an intrinsically motivated agent. Our agent performs satisfactory iterations with the environment, learning complex behaviors without needing previously designed reward functions. We used 18 Atari games to evaluate what cognitive skills emerge in games that require reactive and deliberative behaviors. Our results show superior performance compared to the state-of-the-art in many test cases with dense and sparse rewards.