# Predicting Game Difficulty and Churn Without Players

arXiv: https://arxiv.org/abs/2008.12937 · HTML: https://mlsanity.com/paper/2008.12937/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Aug 2020.

## Built on by (most cited first, 9 of 9)

- [Large Language Models are Pretty Good Zero-Shot Video Game Bug Detectors](https://mlsanity.com/paper/2210.02506/) (2022)
- [RaidEnv: Exploring New Challenges in Automated Content Balancing for Boss Raid Games](https://mlsanity.com/paper/2307.01676/) (2023)
- [Predicting Game Engagement and Difficulty Using AI Players](https://mlsanity.com/paper/2107.12061/) (2021)
- [AI for Games in the Foundation Model Era](https://mlsanity.com/paper/2609.16679/) (2026)
- [Playtesting: What is Beyond Personas](https://mlsanity.com/paper/2107.11965/) (2021)
- [Personalized Game Difficulty Prediction Using Factorization Machines](https://mlsanity.com/paper/2209.13495/) (2022)
- [The Difficulty of Novelty Detection in Open-World Physical Domains: An Application to Angry Birds](https://mlsanity.com/paper/2106.08670/) (2021)
- [A modular framework for automated evaluation of procedural content generation in serious games with deep reinforcement learning agents](https://mlsanity.com/paper/2505.16801/) (2025)
- [Robo-Saber: Generating and Simulating Virtual Reality Players](https://mlsanity.com/paper/2602.18319/) (2026)

## Abstract (arXiv)

We propose a novel simulation model that is able to predict the per-level churn and pass rates of Angry Birds Dream Blast, a popular mobile free-to-play game. Our primary contribution is to combine AI gameplay using Deep Reinforcement Learning (DRL) with a simulation of how the player population evolves over the levels. The AI players predict level difficulty, which is used to drive a player population model with simulated skill, persistence, and boredom. This allows us to model, e.g., how less persistent and skilled players are more sensitive to high difficulty, and how such players churn early, which makes the player population and the relation between difficulty and churn evolve level by level. Our work demonstrates that player behavior predictions produced by DRL gameplay can be significantly improved by even a very simple population-level simulation of individual player differences, without requiring costly retraining of agents or collecting new DRL gameplay data for each simulated player.