# Human-Like Playtesting with Deep Learning

*Source* · `src-gudmundsson-2018-human-like-playtesting` · status: **n/a**

| field | value |
|---|---|
| kind | Peer-reviewed paper |
| authors | S. Gudmundsson, Philipp Eisen, E. Poromaa, Alex Nodet, Sami Purmonen, B. Kozakowski, Richard Meurling, Le-le Cao |
| venue | IEEE Conference on Computational Intelligence and Games (CIG 2018) |
| date | 2018 |
| doi | 10.1109/CIG.2018.8490442 |
| accessed | 2026-10-24 |

## Notes

King: CNN trained on player moves in Candy Crush Saga and Candy Crush Soda Saga predicts human moves and estimates level difficulty; correlates better with average difficulty than MCTS at a fraction of compute.

## Backlinks (computed)

**cited by:** [Agent-based automated playtesting and balancing](../technique/automated-playtesting.md)

## Citation

S. Gudmundsson, Philipp Eisen, E. Poromaa, Alex Nodet, Sami Purmonen, B. Kozakowski, Richard Meurling, Le-le Cao (2018). *Human-Like Playtesting with Deep Learning*. IEEE Conference on Computational Intelligence and Games (CIG 2018) https://doi.org/10.1109/CIG.2018.8490442

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