Identification of Play Styles in Universal Fighting Engine

TL;DR

This paper presents an automated method to compare and evaluate the diversity and human-likeness of play styles in fighting game AI and human players, enhancing the development of believable and varied AI characters.

Contribution

It introduces a novel automated procedure for assessing play style diversity and human-likeness in fighting game AI and human players.

Findings

Effective comparison of AI and human play styles

Quantitative assessment of diversity and human-likeness

Supports development of more believable AI characters

Abstract

AI-controlled characters in fighting games are expected to possess reasonably high skills and behave in a believable, human-like manner, exhibiting a diversity of play styles and strategies. Thus, the development of fighting game AI requires the ability to evaluate these properties. For instance, it should be possible to ensure that the characters created are believable and diverse. In this paper, we show how an automated procedure can be used to compare play styles of individual AI- and human-controlled characters, and to assess human-likeness and diversity of game participants.