Center for Human Modeling and Simulation

Document Type

Conference Paper

Date of this Version

10-2012

Publication Source

AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment

Comments

At the time of publication, author Alla Safonova was affiliated with Disney Research Pittsburgh. Currently, she is a faculty member at the School of Engineering and Applied Science at the University of Pennsylvania.

Abstract

Player metrics are an invaluable resource for game designers and QA analysts who wish to understand players, monitor and improve game play, and test design hypotheses. Usually such metrics are collected in a straightforward manner by passively recording players; however, such an approach has several potential drawbacks. First, passive recording might fail to record metrics which correspond to an infrequent player behavior. Secondly, passive recording can be a costly, laborious, and memory intensive process, even with the aid of tools. In this paper, we explore the potential for an active approach to player metric collection which strives to collect data more efficiently, and thus with less cost. We use an online, iterative approach which models the relationship between player metrics and in-game situations probabilistically using a Markov Decision Process (MDP) and solves it for the best game configurations to run. To analyze the benefits and limitations of this approach, we implemented a system, called GAMELAB, for recording player metrics in Second Life.

Copyright/Permission Statement

Copyright © 2012, Association for the Advancement of Artificial Intelligence. Available at: http://www.aaai.org/ocs/index.php/AIIDE/AIIDE12/paper/view/5458

Keywords

playtesting, data collection, active learning, markov decision process

Share

COinS
 

Date Posted: 13 January 2016