General Video Game Evaluation Using Relative Algorithm Performance Profiles

Thorbjørn Nielsen, Gabriella Barros, Julian Togelius, Mark Nelson

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

Abstrakt

In order to generate complete games through evolution we need generic and reliably evaluation functions for games. It has been suggested that game quality could be characterised through playing a game with different controllers and comparing their performance. This paper explores that idea through investigating the relative performance of different general game-playing algorithms. Seven game-playing algorithms was used to play several hand-designed, mutated and randomly generated VGDL game descriptions. Results discussed appear to support the conjecture that well-designed games have, in average, a higher performance difference between better and worse game-playing algorithms.
OriginalsprogEngelsk
TitelApplications of Evolutionary Computation : 18th European Conference, EvoApplications 2015, Copenhagen, Denmark, April 8-10, 2015, Proceedings
Antal sider12
ForlagSpringer Publishing Company
Publikationsdato2015
Sider369-380
ISBN (Trykt)978-3-319-16548-6
ISBN (Elektronisk)978-3-319-16549-3
DOI
StatusUdgivet - 2015
BegivenhedEvostar 2015: EvoGAMES - Bio-inspired Algorithms in Games - http://www.evostar.org/2015/cfp_evogames.php, Copenhagen, Danmark
Varighed: 8 apr. 201510 apr. 2015
http://www.evostar.org/2015/cfp_evogames.php

Konference

KonferenceEvostar 2015
Lokationhttp://www.evostar.org/2015/cfp_evogames.php
Land/OmrådeDanmark
ByCopenhagen
Periode08/04/201510/04/2015
Internetadresse
NavnLecture Notes in Computer Science
Vol/bind9028
ISSN0302-9743

Fingeraftryk

Dyk ned i forskningsemnerne om 'General Video Game Evaluation Using Relative Algorithm Performance Profiles'. Sammen danner de et unikt fingeraftryk.

Citationsformater