# Transforming Exploratory Creativity with DeLeNoX

arXiv: https://arxiv.org/abs/2103.11715 · HTML: https://mlsanity.com/paper/2103.11715/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 33 references that are in the map.
- First posted on arXiv 22 Mar 2021.

## Built on by (most cited first, 13 of 13)

- [Unsupervised Behaviour Discovery with Quality-Diversity Optimisation](https://mlsanity.com/paper/2106.05648/) (2021)
- [Creativity and Machine Learning: A Survey](https://mlsanity.com/paper/2104.02726/) (2021)
- [Open-Ended Evolution for Minecraft Building Generation](https://mlsanity.com/paper/2209.03108/) (2022)
- [Relevance-guided Unsupervised Discovery of Abilities with Quality-Diversity Algorithms](https://mlsanity.com/paper/2204.09828/) (2022)
- [The Procedural Content Generation Benchmark: An Open-source Testbed for Generative Challenges in Games](https://mlsanity.com/paper/2503.21474/) (2025)
- [Discovering and Exploiting Sparse Rewards in a Learned Behavior Space](https://mlsanity.com/paper/2111.01919/) (2021)
- [Seeding Diversity into AI Art](https://mlsanity.com/paper/2205.00804/) (2022)
- [Hierarchically Composing Level Generators for the Creation of Complex Structures](https://mlsanity.com/paper/2302.01561/) (2023)
- [Leveraging Human Feedback to Evolve and Discover Novel Emergent Behaviors in Robot Swarms](https://mlsanity.com/paper/2305.16148/) (2023)
- [Discovering Unsupervised Behaviours from Full-State Trajectories](https://mlsanity.com/paper/2211.15451/) (2022)
- [Exploring Behavior Discovery Methods for Heterogeneous Swarms of Limited-Capability Robots](https://mlsanity.com/paper/2310.16941/) (2023)
- [JSON-Bag: A generic game trajectory representation](https://mlsanity.com/paper/2508.00712/) (2025)
- [Evolutionary Machine Learning and Games](https://mlsanity.com/paper/2311.16172/) (2023)

## Abstract (arXiv)

We introduce DeLeNoX (Deep Learning Novelty Explorer), a system that autonomously creates artifacts in constrained spaces according to its own evolving interestingness criterion. DeLeNoX proceeds in alternating phases of exploration and transformation. In the exploration phases, a version of novelty search augmented with constraint handling searches for maximally diverse artifacts using a given distance function. In the transformation phases, a deep learning autoencoder learns to compress the variation between the found artifacts into a lower-dimensional space. The newly trained encoder is then used as the basis for a new distance function, transforming the criteria for the next exploration phase. In the current paper, we apply DeLeNoX to the creation of spaceships suitable for use in two-dimensional arcade-style computer games, a representative problem in procedural content generation in games. We also situate DeLeNoX in relation to the distinction between exploratory and transformational creativity, and in relation to Schmidhuber's theory of creativity through the drive for compression progress.