It might be balanced, but is it actually good? An Empirical Evaluation of Game Level Balancing

TL;DR

This paper empirically evaluates the effectiveness of PCGRL in game level balancing by incorporating human perception through playtesting, revealing positive impacts but with scenario-dependent differences.

Contribution

It introduces a human-centered evaluation of PCGRL-generated game levels, addressing the gap of heuristic-only assessments in game balancing.

Findings

PCGRL improves perceived balance in most scenarios

Player perception varies across different balancing scenarios

Empirical evidence supports PCGRL's effectiveness in game design

Abstract

Achieving optimal balance in games is essential to their success, yet reliant on extensive manual work and playtesting. To facilitate this process, the Procedural Content Generation via Reinforcement Learning (PCGRL) framework has recently been effectively used to improve the balance of existing game levels. This approach, however, only assesses balance heuristically, neglecting actual human perception. For this reason, this work presents a survey to empirically evaluate the created content paired with human playtesting. Participants in four different scenarios are asked about their perception of changes made to the level both before and after balancing, and vice versa. Based on descriptive and statistical analysis, our findings indicate that the PCGRL-based balancing positively influences players' perceived balance for most scenarios, albeit with differences in aspects of the balancing between scenarios.