Research Repository

Neuroevolution for General Video Game Playing

Samothrakis, S and Perez-Liebana, D and Lucas, SM and Fasli, M (2015) Neuroevolution for General Video Game Playing. In: UNSPECIFIED, ? - ?.

Full text not available from this repository.

Abstract

© 2015 IEEE. General Video Game Playing (GVGP) allows for the fair evaluation of algorithms and agents as it minimizes the ability of an agent to exploit apriori knowledge in the form of game specific heuristics. In this paper we compare four possible combinations of evolutionary learning using Separable Natural Evolution Strategies as our evolutionary algorithm of choice; linear function approximation with Softmax search and e-greedy policies and neural networks with the same policies. The algorithms explored in this research play each of the games during a sequence of 1000 matches, where the score obtained is used as a measurement of performance. We show that learning is achieved in 8 out of the 10 games employed in this research, without introducing any domain specific knowledge, leading the algorithms to maximize the average score as the number of games played increases.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published proceedings: 2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Jim Jamieson
Date Deposited: 12 Nov 2015 15:58
Last Modified: 17 Aug 2017 17:30
URI: http://repository.essex.ac.uk/id/eprint/15421

Actions (login required)

View Item View Item