# Predicting Game Difficulty and Churn Without Players

*Source* · `src-roohi-2020-difficulty-churn` · status: **n/a**

| field | value |
|---|---|
| kind | Peer-reviewed paper |
| authors | Shaghayegh Roohi, Asko Relas, Jari Takatalo, Henri Heiskanen, Perttu Hämäläinen |
| venue | ACM CHI PLAY 2020 |
| date | 2020-08-29 |
| doi | 10.1145/3410404.3414235 |
| arxiv | 2008.12937 |
| accessed | 2026-10-24 |

## Notes

Deep RL agents estimate level difficulty in Angry Birds Dream Blast; a population model with skill, persistence, and boredom predicts per-level pass and churn rates.

## Backlinks (computed)

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

## Citation

Shaghayegh Roohi, Asko Relas, Jari Takatalo, Henri Heiskanen, Perttu Hämäläinen (2020-08-29). *Predicting Game Difficulty and Churn Without Players*. ACM CHI PLAY 2020 https://doi.org/10.1145/3410404.3414235

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