# Start Small: Training Controllable Game Level Generators without Training Data by Learning at Multiple Sizes

arXiv: https://arxiv.org/abs/2209.15052 · HTML: https://mlsanity.com/paper/2209.15052/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 19 references that are in the map.
- First posted on arXiv 29 Sep 2022.

## Builds on (most cited first, 13 of 13)

- [Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation](https://mlsanity.com/paper/2106.04399/) (2021)
- [PCGRL: Procedural Content Generation via Reinforcement Learning](https://mlsanity.com/paper/2001.09212/) (2020)
- [General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithms](https://mlsanity.com/paper/1802.10363/) (2018)
- [Super Mario as a String: Platformer Level Generation Via LSTMs](https://mlsanity.com/paper/1603.00930/) (2016)
- [Learning Controllable Content Generators](https://mlsanity.com/paper/2105.02993/) (2021)
- [Adversarial Reinforcement Learning for Procedural Content Generation](https://mlsanity.com/paper/2103.04847/) (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)
- [Learning to Generate Levels From Nothing](https://mlsanity.com/paper/2002.05259/) (2020)
- [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)
- [Mutation Models: Learning to Generate Levels by Imitating Evolution](https://mlsanity.com/paper/2206.05497/) (2022)
- [Procedural Content Generation using Neuroevolution and Novelty Search for Diverse Video Game Levels](https://mlsanity.com/paper/2204.06934/) (2022)

## Built on by (most cited first, 2 of 2)

- [Measuring Diversity of Game Scenarios](https://mlsanity.com/paper/2404.15192/) (2024)
- [Improving Conditional Level Generation using Automated Validation in Match-3 Games](https://mlsanity.com/paper/2409.06349/) (2024)

## Abstract (arXiv)

A level generator is a tool that generates game levels from noise. Training a generator without a dataset suffers from feedback sparsity, since it is unlikely to generate a playable level via random exploration. A common solution is shaped rewards, which guides the generator to achieve subgoals towards level playability, but they consume effort to design and require game-specific domain knowledge. This paper proposes a novel approach to train generators without datasets or shaped rewards by learning at multiple level sizes starting from small sizes and up to the desired sizes. The denser feedback at small sizes negates the need for shaped rewards. Additionally, the generators learn to build levels at various sizes, including sizes they were not trained for. We apply our approach to train recurrent auto-regressive generative flow networks (GFlowNets) for controllable level generation. We also adapt diversity sampling to be compatible with GFlowNets. The results show that our generators create diverse playable levels at various sizes for Sokoban, Zelda, and Danger Dave. When compared with controllable reinforcement learning level generators for Sokoban, the results show that our generators achieve better controllability and competitive diversity, while being 9x faster at training and level generation.