Seminar: Exploring Options for Efficiently Evaluating the Playability of Computer Game Agents

Todd Wareham
Department of Computer Science
Memorial University of Newfoundland

Exploring Options for Efficiently Evaluating the Playability of Computer Game Agents

Department of Computer Science
Thursday, February 19, 2015, 1:00 p.m., Room EN-2022


 

Abstract

Automatic generation of game content is an important challenge in computer game design. Such generation requires efficient methods for automatically evaluating the playability of generated content. Research to date has focused on the evaluation of game levels. However, the increasing importance of game play involving complex non-player agents (for example, agents capable of exchanging items and facts with each other and human players) suggests that methods for automatically evaluating the playability of groups of such agentsshould also be investigated. In this talk, I will describe an augmented finite-state machine model for agents with item and fact exchange capabilities and illustrate how computational complexity analysis can be used to explore the sets of restrictions under which efficient playability evaluation of groups of such agents is and is not possible.

Work done with Scott Watson (Department of Computer Science, Memorial University of Newfoundland)

Contact

Department of Computer Science

230 Elizabeth Ave

St. John's, NL A1B 3X9 CANADA

Tel: (709) 864-2530

Fax: (709) 864-2552

becomestudent@mun.ca