# Mutation Models: Learning to Generate Levels by Imitating Evolution

arXiv: https://arxiv.org/abs/2206.05497 · HTML: https://mlsanity.com/paper/2206.05497/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 47 references that are in the map.
- First posted on arXiv 11 Jun 2022.

## Builds on (most cited first, 23 of 23)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Go-Explore: a New Approach for Hard-Exploration Problems](https://mlsanity.com/paper/1901.10995/) (2019)
- [Procedural Content Generation via Machine Learning (PCGML)](https://mlsanity.com/paper/1702.00539/) (2017)
- [PCGRL: Procedural Content Generation via Reinforcement Learning](https://mlsanity.com/paper/2001.09212/) (2020)
- [Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network](https://mlsanity.com/paper/1805.00728/) (2018)
- [Deep Learning for Procedural Content Generation](https://mlsanity.com/paper/2010.04548/) (2020)
- [General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithms](https://mlsanity.com/paper/1802.10363/) (2018)
- [Learning Controllable Content Generators](https://mlsanity.com/paper/2105.02993/) (2021)
- [Bootstrapping Conditional GANs for Video Game Level Generation](https://mlsanity.com/paper/1910.01603/) (2019)
- [Illuminating Diverse Neural Cellular Automata for Level Generation](https://mlsanity.com/paper/2109.05489/) (2021)
- [Friend, Collaborator, Student, Manager: How Design of an AI-Driven Game Level Editor Affects Creators](https://mlsanity.com/paper/1901.06417/) (2019)
- [Experience-Driven PCG via Reinforcement Learning: A Super Mario Bros Study](https://mlsanity.com/paper/2106.15877/) (2021)
- [Rotation, Translation, and Cropping for Zero-Shot Generalization](https://mlsanity.com/paper/2001.09908/) (2020)
- [Co-Creative Level Design via Machine Learning](https://mlsanity.com/paper/1809.09420/) (2018)
- [General Video Game Rule Generation](https://mlsanity.com/paper/1906.05160/) (2019)
- [Path of Destruction: Learning an Iterative Level Generator Using a Small Dataset](https://mlsanity.com/paper/2202.10184/) (2022)
- [Mixed-Initiative Level Design with RL Brush](https://mlsanity.com/paper/2008.02778/) (2020)
- [Dungeon and Platformer Level Blending and Generation using Conditional VAEs](https://mlsanity.com/paper/2106.12692/) (2021)
- [Multi-Objective level generator generation with Marahel](https://mlsanity.com/paper/2005.08368/) (2020)
- [Q-DeckRec: A Fast Deck Recommendation System for Collectible Card Games](https://mlsanity.com/paper/1806.09771/) (2018)
- [Arachnophobia Exposure Therapy using Experience-driven Procedural Content Generation via Reinforcement Learning (EDPCGRL)](https://mlsanity.com/paper/2110.04146/) (2021)

## Built on by (most cited first, 9 of 9)

- [Stabilizing Unsupervised Environment Design with a Learned Adversary](https://mlsanity.com/paper/2308.10797/) (2023)
- [Balancing of competitive two-player Game Levels with Reinforcement Learning](https://mlsanity.com/paper/2306.04429/) (2023)
- [Start Small: Training Controllable Game Level Generators without Training Data by Learning at Multiple Sizes](https://mlsanity.com/paper/2209.15052/) (2022)
- [Learning Curricula in Open-Ended Worlds](https://mlsanity.com/paper/2312.03126/) (2023)
- [Evolutionary Machine Learning and Games](https://mlsanity.com/paper/2311.16172/) (2023)
- [Simulation-Driven Balancing of Competitive Game Levels with Reinforcement Learning](https://mlsanity.com/paper/2503.18748/) (2025)
- [Evolutionary Level Repair](https://mlsanity.com/paper/2506.19359/) (2025)
- [A Markovian Framing of WaveFunctionCollapse for Procedurally Generating Aesthetically Complex Environments](https://mlsanity.com/paper/2509.09919/) (2025)
- [Continuous Program Search](https://mlsanity.com/paper/2602.07659/) (2026)

## Abstract (arXiv)

Search-based procedural content generation (PCG) is a well-known method for level generation in games. Its key advantage is that it is generic and able to satisfy functional constraints. However, due to the heavy computational costs to run these algorithms online, search-based PCG is rarely utilized for real-time generation. In this paper, we introduce mutation models, a new type of iterative level generator based on machine learning. We train a model to imitate the evolutionary process and use the trained model to generate levels. This trained model is able to modify noisy levels sequentially to create better levels without the need for a fitness function during inference. We evaluate our trained models on a 2D maze generation task. We compare several different versions of the method: training the models either at the end of evolution (normal evolution) or every 100 generations (assisted evolution) and using the model as a mutation function during evolution. Using the assisted evolution process, the final trained models are able to generate mazes with a success rate of 99% and high diversity of 86%. The trained model is many times faster than the evolutionary process it was trained on. This work opens the door to a new way of learning level generators guided by an evolutionary process, meaning automatic creation of generators with specifiable constraints and objectives that are fast enough for runtime deployment in games.