Monte-Carlo Tree Search for Persona Based Player Modeling

Authors

  • Christoffer Holmgård IT University of Copenhagen
  • Antonios Liapis University of Malta
  • Julian Togelius New York University
  • Georgios Yannakakis University of Malta

DOI:

https://doi.org/10.1609/aiide.v11i5.12849

Abstract

Is it possible to conduct player modeling without any players? In this paper we use Monte-Carlo Tree Search-controlled procedural personas to simulate a range of decision making styles in the puzzle game MiniDungeons 2. The purpose is to provide a method for synthetic play testing of game levels with synthetic players based on designer intuition and experience. Five personas are constructed, representing five different decision making styles archetypal for the game. The personas vary solely in the weights of decision-making utilities that describe their valuation of a set affordances in MiniDungeons 2. By configuring these weights using designer expert knowledge, and passing the configurations directly to the MCTS algorithm, we make the personas exhibit a number of distinct decision making and play styles.

Downloads

Published

2021-06-24

How to Cite

Holmgård, C., Liapis, A., Togelius, J., & Yannakakis, G. (2021). Monte-Carlo Tree Search for Persona Based Player Modeling. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 11(5), 8-14. https://doi.org/10.1609/aiide.v11i5.12849

Issue

Vol. 11 No. 5 (2015): AIIDE Workshop Technical Report WS-15-23 (Player Modeling)

Section

Player Modeling