# Illuminating the Space of Beatable Lode Runner Levels Produced By Various Generative Adversarial Networks

arXiv: https://arxiv.org/abs/2101.07868 · HTML: https://mlsanity.com/paper/2101.07868/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 19 Jan 2021.

## Builds on (most cited first, 11 of 11)

- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network](https://mlsanity.com/paper/1805.00728/) (2018)
- [Illuminating Mario Scenes in the Latent Space of a Generative Adversarial Network](https://mlsanity.com/paper/2007.05674/) (2020)
- [The VGLC: The Video Game Level Corpus](https://mlsanity.com/paper/1606.07487/) (2016)
- [Bootstrapping Conditional GANs for Video Game Level Generation](https://mlsanity.com/paper/1910.01603/) (2019)
- [Interactive Evolution and Exploration Within Latent Level-Design Space of Generative Adversarial Networks](https://mlsanity.com/paper/2004.00151/) (2020)
- [TOAD-GAN: Coherent Style Level Generation from a Single Example](https://mlsanity.com/paper/2008.01531/) (2020)
- [CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-scale Pattern Generation](https://mlsanity.com/paper/2004.01703/) (2020)
- [Generative Adversarial Network Rooms in Generative Graph Grammar Dungeons for The Legend of Zelda](https://mlsanity.com/paper/2001.05065/) (2020)
- [DeepMasterPrints: Generating MasterPrints for Dictionary Attacks via Latent Variable Evolution](https://mlsanity.com/paper/1705.07386/) (2017)

## Built on by (most cited first, 14 of 14)

- [Differentiable Quality Diversity](https://mlsanity.com/paper/2106.03894/) (2021)
- [Deep Surrogate Assisted Generation of Environments](https://mlsanity.com/paper/2206.04199/) (2022)
- [Covariance Matrix Adaptation MAP-Annealing](https://mlsanity.com/paper/2205.10752/) (2022)
- [Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning](https://mlsanity.com/paper/2305.13795/) (2023)
- [Dungeon and Platformer Level Blending and Generation using Conditional VAEs](https://mlsanity.com/paper/2106.12692/) (2021)
- [Surrogate Assisted Generation of Human-Robot Interaction Scenarios](https://mlsanity.com/paper/2304.13787/) (2023)
- [Online Damage Recovery for Physical Robots with Hierarchical Quality-Diversity](https://mlsanity.com/paper/2210.09918/) (2022)
- [Lode Encoder: AI-constrained co-creativity](https://mlsanity.com/paper/2308.01312/) (2023)
- [Hierarchical Quality-Diversity for Online Damage Recovery](https://mlsanity.com/paper/2204.05726/) (2022)
- [Measuring Diversity of Game Scenarios](https://mlsanity.com/paper/2404.15192/) (2024)
- [Using Multiple Generative Adversarial Networks to Build Better-Connected Levels for Mega Man](https://mlsanity.com/paper/2102.00337/) (2021)
- [Lode Enhancer: Level Co-creation Through Scaling](https://mlsanity.com/paper/2308.01543/) (2023)
- [Discount Model Search for Quality Diversity Optimization in High-Dimensional Measure Spaces](https://mlsanity.com/paper/2601.01082/) (2026)
- [Learning Local Constraints for Reinforcement-Learned Content Generators](https://mlsanity.com/paper/2605.13570/) (2026)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) are capable of generating convincing imitations of elements from a training set, but the distribution of elements in the training set affects to difficulty of properly training the GAN and the quality of the outputs it produces. This paper looks at six different GANs trained on different subsets of data from the game Lode Runner. The quality diversity algorithm MAP-Elites was used to explore the set of quality levels that could be produced by each GAN, where quality was defined as being beatable and having the longest solution path possible. Interestingly, a GAN trained on only 20 levels generated the largest set of diverse beatable levels while a GAN trained on 150 levels generated the smallest set of diverse beatable levels, thus challenging the notion that more is always better when training GANs.