# Improving Conditional Level Generation using Automated Validation in Match-3 Games

*Source* · `src-villanueva-2024-match3-conditional-generation` · status: **n/a**

| field | value |
|---|---|
| kind | Peer-reviewed paper |
| authors | Monica Villanueva Aylagas, Joakim Bergdahl, Jonas Gillberg, Alessandro Sestini, Theodor Tolstoy, Linus Gisslén |
| venue | IEEE Transactions on Games |
| date | 2024 |
| url | https://media.contentapi.ea.com/content/dam/ea/seed/presentations/seed-tog-conditional-level-generation-paper.pdf |
| doi | 10.1109/TG.2024.3440214 |
| accessed | 2026-10-24 |

## Notes

EA SEED cVAE conditioned on size, symmetry, and difficulty (median moves of a scripted bot over 30 plays); 51.39% valid levels versus 46.15% in the dataset; difficulty accuracy 33.33%, mean gap 10.19 moves.

## Backlinks (computed)

**cited by:** [Learned level and map generation (PCGRL, MarioGPT, LLM generators)](../technique/learned-level-generation.md)

## Citation

Monica Villanueva Aylagas, Joakim Bergdahl, Jonas Gillberg, Alessandro Sestini, Theodor Tolstoy, Linus Gisslén (2024). *Improving Conditional Level Generation using Automated Validation in Match-3 Games*. IEEE Transactions on Games https://media.contentapi.ea.com/content/dam/ea/seed/presentations/seed-tog-conditional-level-generation-paper.pdf

---
Provenance: created in run `2026-10-24-techniques-rl-design`.