# Learning to Generate Levels From Nothing

arXiv: https://arxiv.org/abs/2002.05259 · HTML: https://mlsanity.com/paper/2002.05259/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2020.

## Built on by (most cited first, 17 of 17)

- [Learning Controllable 3D Level Generators](https://mlsanity.com/paper/2206.13623/) (2022)
- [A Definition of Open-Ended Learning Problems for Goal-Conditioned Agents](https://mlsanity.com/paper/2311.00344/) (2023)
- [DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraft](https://mlsanity.com/paper/2404.15538/) (2024)
- [DreamGarden: A Designer Assistant for Growing Games from a Single Prompt](https://mlsanity.com/paper/2410.01791/) (2024)
- [Adversarial Environment Design via Regret-Guided Diffusion Models](https://mlsanity.com/paper/2410.19715/) (2024)
- [Hierarchically Composing Level Generators for the Creation of Complex Structures](https://mlsanity.com/paper/2302.01561/) (2023)
- [Balancing of competitive two-player Game Levels with Reinforcement Learning](https://mlsanity.com/paper/2306.04429/) (2023)
- [Active Task Randomization: Learning Robust Skills via Unsupervised Generation of Diverse and Feasible Tasks](https://mlsanity.com/paper/2211.06134/) (2022)
- [Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents](https://mlsanity.com/paper/2407.04221/) (2024)
- [Watts: Infrastructure for Open-Ended Learning](https://mlsanity.com/paper/2204.13250/) (2022)
- [Start Small: Training Controllable Game Level Generators without Training Data by Learning at Multiple Sizes](https://mlsanity.com/paper/2209.15052/) (2022)
- [PCGPT: Procedural Content Generation via Transformers](https://mlsanity.com/paper/2310.02405/) (2023)
- [Analysis of Robustness of a Large Game Corpus](https://mlsanity.com/paper/2504.03940/) (2025)
- [Improving Conditional Level Generation using Automated Validation in Match-3 Games](https://mlsanity.com/paper/2409.06349/) (2024)
- [Simulation-Driven Balancing of Competitive Game Levels with Reinforcement Learning](https://mlsanity.com/paper/2503.18748/) (2025)
- [Expanding Horizons of Level Diversity via Multi-objective Evolutionary Learning](https://mlsanity.com/paper/2509.24341/) (2025)
- [LLM-Driven 3D Scene Generation of Agricultural Simulation Environments](https://mlsanity.com/paper/2602.11706/) (2026)

## Abstract (arXiv)

Machine learning for procedural content generation has recently become an active area of research. Levels vary in both form and function and are mostly unrelated to each other across games. This has made it difficult to assemble suitably large datasets to bring machine learning to level design in the same way as it's been used for image generation. Here we propose Generative Playing Networks which design levels for itself to play. The algorithm is built in two parts; an agent that learns to play game levels, and a generator that learns the distribution of playable levels. As the agent learns and improves its ability, the space of playable levels, as defined by the agent, grows. The generator targets the agent's playability estimates to then update its understanding of what constitutes a playable level. We call this process of learning the distribution of data found through self-discovery with an environment, self-supervised inductive learning. Unlike previous approaches to procedural content generation, Generative Playing Networks are end-to-end differentiable and do not require human-designed examples or domain knowledge. We demonstrate the capability of this framework by training an agent and level generator for a 2D dungeon crawler game.