# Estimating player completion rate in mobile puzzle games using reinforcement learning

arXiv: https://arxiv.org/abs/2306.14626 · HTML: https://mlsanity.com/paper/2306.14626/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 8 references that are in the map.
- First posted on arXiv 26 Jun 2023.

## Builds on (most cited first, 4 of 4)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Automated Playtesting with Procedural Personas through MCTS with Evolved Heuristics](https://mlsanity.com/paper/1802.06881/) (2018)
- [Automated Playtesting of Matching Tile Games](https://mlsanity.com/paper/1907.06570/) (2019)
- [Strategies for Using Proximal Policy Optimization in Mobile Puzzle Games](https://mlsanity.com/paper/2007.01542/) (2020)

## Built on by (most cited first, 3 of 3)

- [RaidEnv: Exploring New Challenges in Automated Content Balancing for Boss Raid Games](https://mlsanity.com/paper/2307.01676/) (2023)
- [Difficulty Modelling in Mobile Puzzle Games: An Empirical Study on Different Methods to Combine Player Analytics and Simulated Data](https://mlsanity.com/paper/2401.17436/) (2024)
- [Robo-Saber: Generating and Simulating Virtual Reality Players](https://mlsanity.com/paper/2602.18319/) (2026)

## Abstract (arXiv)

In this work we investigate whether it is plausible to use the performance of a reinforcement learning (RL) agent to estimate the difficulty measured as the player completion rate of different levels in the mobile puzzle game Lily's Garden.For this purpose we train an RL agent and measure the number of moves required to complete a level. This is then compared to the level completion rate of a large sample of real players.We find that the strongest predictor of player completion rate for a level is the number of moves taken to complete a level of the ~5% best runs of the agent on a given level. A very interesting observation is that, while in absolute terms, the agent is unable to reach human-level performance across all levels, the differences in terms of behaviour between levels are highly correlated to the differences in human behaviour. Thus, despite performing sub-par, it is still possible to use the performance of the agent to estimate, and perhaps further model, player metrics.