# Curiosity Driven Exploration of Learned Disentangled Goal Spaces

arXiv: https://arxiv.org/abs/1807.01521 · HTML: https://mlsanity.com/paper/1807.01521/

## Key facts

- Cited by 16 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 4 Jul 2018.

## Built on by (most cited first, 16 of 16)

- [Symmetry-Based Representations for Artificial and Biological General Intelligence](https://mlsanity.com/paper/2203.09250/) (2022)
- [Rule-Based Reinforcement Learning for Efficient Robot Navigation with Space Reduction](https://mlsanity.com/paper/2104.07282/) (2021)
- [DisCo RL: Distribution-Conditioned Reinforcement Learning for General-Purpose Policies](https://mlsanity.com/paper/2104.11707/) (2021)
- [DisTop: Discovering a Topological representation to learn diverse and rewarding skills](https://mlsanity.com/paper/2106.03853/) (2021)
- [Online Damage Recovery for Physical Robots with Hierarchical Quality-Diversity](https://mlsanity.com/paper/2210.09918/) (2022)
- [MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces](https://mlsanity.com/paper/2502.07709/) (2025)
- [ACES: Generating Diverse Programming Puzzles with with Autotelic Generative Models](https://mlsanity.com/paper/2310.10692/) (2023)
- [Discovering and Exploiting Sparse Rewards in a Learned Behavior Space](https://mlsanity.com/paper/2111.01919/) (2021)
- [Hierarchical Quality-Diversity for Online Damage Recovery](https://mlsanity.com/paper/2204.05726/) (2022)
- [Predictive World Models from Real-World Partial Observations](https://mlsanity.com/paper/2301.04783/) (2023)
- [Disentangled (Un)Controllable Features](https://mlsanity.com/paper/2211.00086/) (2022)
- [A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making](https://mlsanity.com/paper/2304.10590/) (2023)
- [Disentangled Representations for Causal Cognition](https://mlsanity.com/paper/2407.00744/) (2024)
- [Wind Estimation in Unmanned Aerial Vehicles with Causal Machine Learning](https://mlsanity.com/paper/2407.01154/) (2024)
- [Parameter Estimation using Reinforcement Learning Causal Curiosity: Limits and Challenges](https://mlsanity.com/paper/2505.08453/) (2025)
- [Distilling a Modular Reservoir Through a Genomic Bottleneck](https://mlsanity.com/paper/2606.28380/) (2026)

## Abstract (arXiv)

Intrinsically motivated goal exploration processes enable agents to autonomously sample goals to explore efficiently complex environments with high-dimensional continuous actions. They have been applied successfully to real world robots to discover repertoires of policies producing a wide diversity of effects. Often these algorithms relied on engineered goal spaces but it was recently shown that one can use deep representation learning algorithms to learn an adequate goal space in simple environments. However, in the case of more complex environments containing multiple objects or distractors, an efficient exploration requires that the structure of the goal space reflects the one of the environment. In this paper we show that using a disentangled goal space leads to better exploration performances than an entangled goal space. We further show that when the representation is disentangled, one can leverage it by sampling goals that maximize learning progress in a modular manner. Finally, we show that the measure of learning progress, used to drive curiosity-driven exploration, can be used simultaneously to discover abstract independently controllable features of the environment.