Monte-Carlo Tree Search for Simulation-based Strategy Analysis

TL;DR

This paper introduces a method using Monte-Carlo Tree Search to simulate human players of different skill levels, enabling automated evaluation of game design and balance without extensive human playtesting.

Contribution

It presents a novel approach to analyze game design by employing simulation agents with varying skill levels to generate gameplay metrics.

Findings

Simulated agents can effectively evaluate game balance in Scrabble.

The approach identifies potential design flaws in Cardonomicon.

Automated analysis reduces reliance on human playtesting.

Abstract

Games are often designed to shape player behavior in a desired way; however, it can be unclear how design decisions affect the space of behaviors in a game. Designers usually explore this space through human playtesting, which can be time-consuming and of limited effectiveness in exhausting the space of possible behaviors. In this paper, we propose the use of automated planning agents to simulate humans of varying skill levels to generate game playthroughs. Metrics can then be gathered from these playthroughs to evaluate the current game design and identify its potential flaws. We demonstrate this technique in two games: the popular word game Scrabble and a collectible card game of our own design named Cardonomicon. Using these case studies, we show how using simulated agents to model humans of varying skill levels allows us to extract metrics to describe game balance (in the case of Scrabble) and highlight potential design flaws (in the case of Cardonomicon).