Analysis of Uncertainty in Procedural Maps in Slay the Spire

2025-04-04

AI Summary

This study investigates how path uncertainty introduced by procedural map generation in *Slay the Spire* affects player decision-making and win rates. Leveraging 20,000 real-game trajectories, we propose normalized path entropy as a quantifiable risk metric, integrating information-theoretic entropy computation with statistical modeling to analyze its correlation with match outcomes and player skill level. Results show that winning trajectories exhibit significantly higher path entropy; moreover, high-skill players adopt deliberate high-entropy (i.e., high-risk) strategies during mid-to-late game phases—distinct from low-skill players. This work is the first to model path entropy as a dynamic behavioral proxy for risk-taking, empirically revealing stage-dependent risk-preference stratification across skill levels. It thus provides an interpretable, measurable theoretical foundation and practical framework for calibrating uncertainty in procedurally generated level design.

Technology Category

• Reasoning under Uncertainty: Sequential Decision Making
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Planning, Routing, and Scheduling: Planning under Uncertainty

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

This work investigates the role of uncertainty in Slay the Spire using an information-theoretic framework. Focusing on the entropy of game paths (which are based on procedurally-generated maps) we analyze how randomness influences player decision-making and success. By examining a dataset of 20,000 game runs, we quantify the entropy of paths taken by players and relate it with their outcomes and skill levels. The results show that victorious runs are associated with higher normalized entropy, suggesting more risk-taking. Additionally, higher-skill players tend to exhibit distinct patterns of risk-taking behavior in later game stages.

Problem

• Analyzing uncertainty in Slay the Spire's procedural maps
• Quantifying entropy impact on player decisions and success
• Linking risk-taking behavior to victory and skill levels

Innovation

• Information-theoretic framework analyzes game uncertainty
• Quantifies entropy of paths from 20,000 runs
• Links normalized entropy with player success