Automated Playtesting with Procedural Personas through MCTS with Evolved Heuristics

TL;DR

This paper introduces a novel method for automatic game content testing using AI-driven procedural personas modeled with an evolved Monte Carlo Tree Search, enabling rapid and diverse playtesting without human input.

Contribution

It presents a new approach combining procedural personas with evolved MCTS for automated game testing, grounded in psychological decision theory.

Findings

Effective generation of diverse play styles

Application to varied game levels demonstrated

Potential for rapid, automated playtesting

Abstract

This paper describes a method for generative player modeling and its application to the automatic testing of game content using archetypal player models called procedural personas. Theoretically grounded in psychological decision theory, procedural personas are implemented using a variation of Monte Carlo Tree Search (MCTS) where the node selection criteria are developed using evolutionary computation, replacing the standard UCB1 criterion of MCTS. Using these personas we demonstrate how generative player models can be applied to a varied corpus of game levels and demonstrate how different play styles can be enacted in each level. In short, we use artificially intelligent personas to construct synthetic playtesters. The proposed approach could be used as a tool for automatic play testing when human feedback is not readily available or when quick visualization of potential interactions is necessary. Possible applications include interactive tools during game development or procedural content generation systems where many evaluations must be conducted within a short time span.