Document Type

Conference Proceeding

Publication Date

2017

Abstract

Being able to imitate individual players in a game can benefit game development by providing a means to create a variety of autonomous agents and aid understanding of which aspects of game states influence game-play. This paper presents a clustering and locally weighted regression method for modeling and imitating individual players. The algorithm first learns a generic player cluster model that is updated online to capture an individual’s game-play tendencies. The models can then be used to play the game or for analysis to identify how different players react to separate aspects of game states. The method is demonstrated on a tablet-based trajectory generation game called Space Navigator.

Comments

© 2017 Springer International Publishing AG (outside the US).

AFIT Scholar furnishes the draft version of this chapter. The published version is available to subscribers at the Springer website through the DOI link in the citation below.

This work was supported in part through the Air Force Office of Scientific Research, Computational Cognition & Robust Decision Making Program (FA9550)

DOI

https://doi.org/10.1007/978-3-319-57969-6_7

Source Publication

Communications in Computer and Information Science, vol 705

COinS