Co-evolutionary Learning for Cognitive Computer Generated Entities

W.X. Wilcke; M. Hoogendoorn; J.J.M. Roessingh

doi:10.1007/978-3-319-07467-2_13

Co-evolutionary Learning for Cognitive Computer Generated Entities

W.X. Wilcke, M. Hoogendoorn, J.J.M. Roessingh

Research output: Contribution to Journal › Article › Academic › peer-review

Abstract

In this paper, an approach is advocated to use a hybrid approach towards learning behaviour for computer generated entities (CGEs) in a serious gaming setting. Hereby, an agent equipped with cognitive model is used but this agent is enhanced with Machine Learning (ML) capabilities. This facilitates the agent to exhibit human like behaviour but avoid an expert having to define all parameters explicitly. More in particular, the ML approach utilizes co-evolution as a learning paradigm. An evaluation in the domain of one-versus-one air combat shows promising results.

Original language	English
Pages (from-to)	120-129
Journal	Lecture Notes in Computer Science
Volume	8482
Issue number	2
DOIs	https://doi.org/10.1007/978-3-319-07467-2_13
Publication status	Published - 2014
Event	27th International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems - Duration: 3 Jun 2014 → 6 Jun 2014

Bibliographical note

Proceedings title: Modern Advances in Applied Intelligence
Publisher: Springer International Publishing
ISBN: 978-3-319-07466-5
Editors: M Ali, JS Pan, SM Chen, MF Horng

Access to Document

10.1007/978-3-319-07467-2_13

http://reports.nlr.nl:8080/xmlui/bitstream/handle/10921/971/TP-2014-157.pdf?sequence=1

Cite this

@article{bcc9ad6004d04da0be9e7c596a980e6f,

title = "Co-evolutionary Learning for Cognitive Computer Generated Entities",

abstract = "In this paper, an approach is advocated to use a hybrid approach towards learning behaviour for computer generated entities (CGEs) in a serious gaming setting. Hereby, an agent equipped with cognitive model is used but this agent is enhanced with Machine Learning (ML) capabilities. This facilitates the agent to exhibit human like behaviour but avoid an expert having to define all parameters explicitly. More in particular, the ML approach utilizes co-evolution as a learning paradigm. An evaluation in the domain of one-versus-one air combat shows promising results.",

author = "W.X. Wilcke and M. Hoogendoorn and J.J.M. Roessingh",

note = "Proceedings title: Modern Advances in Applied Intelligence Publisher: Springer International Publishing ISBN: 978-3-319-07466-5 Editors: M Ali, JS Pan, SM Chen, MF Horng; 27th International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems ; Conference date: 03-06-2014 Through 06-06-2014",

year = "2014",

doi = "10.1007/978-3-319-07467-2_13",

language = "English",

volume = "8482",

pages = "120--129",

journal = "Lecture Notes in Computer Science",

issn = "0302-9743",

publisher = "Springer Verlag",

number = "2",

}

TY - JOUR

T1 - Co-evolutionary Learning for Cognitive Computer Generated Entities

AU - Wilcke, W.X.

AU - Hoogendoorn, M.

AU - Roessingh, J.J.M.

N1 - Proceedings title: Modern Advances in Applied Intelligence Publisher: Springer International Publishing ISBN: 978-3-319-07466-5 Editors: M Ali, JS Pan, SM Chen, MF Horng

PY - 2014

Y1 - 2014

N2 - In this paper, an approach is advocated to use a hybrid approach towards learning behaviour for computer generated entities (CGEs) in a serious gaming setting. Hereby, an agent equipped with cognitive model is used but this agent is enhanced with Machine Learning (ML) capabilities. This facilitates the agent to exhibit human like behaviour but avoid an expert having to define all parameters explicitly. More in particular, the ML approach utilizes co-evolution as a learning paradigm. An evaluation in the domain of one-versus-one air combat shows promising results.

AB - In this paper, an approach is advocated to use a hybrid approach towards learning behaviour for computer generated entities (CGEs) in a serious gaming setting. Hereby, an agent equipped with cognitive model is used but this agent is enhanced with Machine Learning (ML) capabilities. This facilitates the agent to exhibit human like behaviour but avoid an expert having to define all parameters explicitly. More in particular, the ML approach utilizes co-evolution as a learning paradigm. An evaluation in the domain of one-versus-one air combat shows promising results.

U2 - 10.1007/978-3-319-07467-2_13

DO - 10.1007/978-3-319-07467-2_13

M3 - Article

VL - 8482

SP - 120

EP - 129

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

SN - 0302-9743

IS - 2

T2 - 27th International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems

Y2 - 3 June 2014 through 6 June 2014

ER -

Co-evolutionary Learning for Cognitive Computer Generated Entities

Abstract

Bibliographical note

Access to Document

Fingerprint

Cite this