ITU

Neuroevolution in Games: State of the Art and Open Challenges

Research output: Journal Article or Conference Article in JournalJournal articleResearchpeer-review

Standard

Neuroevolution in Games: State of the Art and Open Challenges. / Risi, Sebastian; Togelius, Julian.

In: I E E E Transactions on Computational Intelligence and A I in Games, Vol. 9, No. 1, 2015, p. 25-41.

Research output: Journal Article or Conference Article in JournalJournal articleResearchpeer-review

Harvard

APA

Vancouver

Author

Bibtex

@article{b2671ae3f11c4935811efb729ccdbcce,
title = "Neuroevolution in Games: State of the Art and Open Challenges",
abstract = "This paper surveys research on applying neuroevolution(NE) to games. In neuroevolution, artificial neural networksare trained through evolutionary algorithms, taking inspirationfrom the way biological brains evolved. We analyse theapplication of NE in games along five different axes, which are therole NE is chosen to play in a game, the different types of neuralnetworks used, the way these networks are evolved, how thefitness is determined and what type of input the network receives.The article also highlights important open research challenges inthe field.",
author = "Sebastian Risi and Julian Togelius",
year = "2015",
doi = "10.1109/TCIAIG.2015.2494596",
language = "English",
volume = "9",
pages = "25--41",
journal = "I E E E Transactions on Computational Intelligence and A I in Games",
issn = "1943-068X",
publisher = "institute of electrical and electronics engineers (ieee)",
number = "1",

}

RIS

TY - JOUR

T1 - Neuroevolution in Games: State of the Art and Open Challenges

AU - Risi, Sebastian

AU - Togelius, Julian

PY - 2015

Y1 - 2015

N2 - This paper surveys research on applying neuroevolution(NE) to games. In neuroevolution, artificial neural networksare trained through evolutionary algorithms, taking inspirationfrom the way biological brains evolved. We analyse theapplication of NE in games along five different axes, which are therole NE is chosen to play in a game, the different types of neuralnetworks used, the way these networks are evolved, how thefitness is determined and what type of input the network receives.The article also highlights important open research challenges inthe field.

AB - This paper surveys research on applying neuroevolution(NE) to games. In neuroevolution, artificial neural networksare trained through evolutionary algorithms, taking inspirationfrom the way biological brains evolved. We analyse theapplication of NE in games along five different axes, which are therole NE is chosen to play in a game, the different types of neuralnetworks used, the way these networks are evolved, how thefitness is determined and what type of input the network receives.The article also highlights important open research challenges inthe field.

U2 - 10.1109/TCIAIG.2015.2494596

DO - 10.1109/TCIAIG.2015.2494596

M3 - Journal article

VL - 9

SP - 25

EP - 41

JO - I E E E Transactions on Computational Intelligence and A I in Games

JF - I E E E Transactions on Computational Intelligence and A I in Games

SN - 1943-068X

IS - 1

ER -

ID: 81023292