Document Type

Conference Proceeding

Publisher

IEEE

Faculty

Computing, Health and Science

School

School of Computer & Security Science

RAS ID

10102

Comments

This article was originally published as: Hingston, P. F. (2010). A New Design for a Turing Test for Bots. Proceedings of 2010 IEEE Conference on Computational Intelligence and Games (CIG'10). (pp. 345-350). . IT University Copenhagen, Denmark. IEEE. Original article available here

© 2010 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Abstract

Interesting, human-like opponents add to the entertainment value of a video game, and creating such opponents is a difficult challenge for programmers. Can artificial intelligence and computational intelligence provide the means to convincingly simulate a human opponent? Or are simple programming tricks and deceptions more effective? To answer these questions, the author designed and organised a game bot programming competition, the BotPrize, in which competitors submit bots that try to pass a “Turing Test for Bots”. In this paper, we describe a new design for the competition, which will make it simpler to run, and, we hope, open up new opportunities for innovative use of the testing platform. We illustrate the potential of the new platform by describing an implementation of a bot that is designed to learn how to appear more human using feedback obtained during play.

DOI

10.1109/ITW.2010.5593336

Access Rights

free_to_read

 
COinS
 

Link to publisher version (DOI)

10.1109/ITW.2010.5593336