Hierarchical behaviours : getting the most bang for your bit

S. van Dijk; D. Polani; C.L. Nehaniv

doi:10.1007/978-3-642-21314-4_43

Hierarchical behaviours : getting the most bang for your bit

S. van Dijk, D. Polani, C.L. Nehaniv

Research output: Contribution to journal › Article › peer-review

10 Citations (Scopus)

46 Downloads (Pure)

Abstract

Hierarchical structuring of behaviour is prevalent in natural and artificial agents and can be shown to be useful for learning and performing tasks. To progress systematic understanding of these benefits we study the effect of hierarchical architectures on the required information processing capability of an optimally acting agent. We show that an information-theoretical approach provides important insights into why factored and layered behaviour structures are beneficial.

Original language	English
Pages (from-to)	342-349
Journal	Lecture Notes in Computer Science (LNCS)
Volume	5778
DOIs	https://doi.org/10.1007/978-3-642-21314-4_43
Publication status	Published - 2011
Event	European Conference on Artificial Life - Budapest, United Kingdom Duration: 13 Sept 2009 → 16 Sept 2009

Access to Document

10.1007/978-3-642-21314-4_43

903564
The original publication is available at www.springerlink.com
Accepted author manuscript, 167 KB

Cite this

@article{09ae2e7627c343c9bf05e812caff9c6b,

title = "Hierarchical behaviours : getting the most bang for your bit",

abstract = "Hierarchical structuring of behaviour is prevalent in natural and artificial agents and can be shown to be useful for learning and performing tasks. To progress systematic understanding of these benefits we study the effect of hierarchical architectures on the required information processing capability of an optimally acting agent. We show that an information-theoretical approach provides important insights into why factored and layered behaviour structures are beneficial.",

author = "{van Dijk}, S. and D. Polani and C.L. Nehaniv",

note = "“The original publication is available at www.springerlink.com” Copyright Springer; European Conference on Artificial Life ; Conference date: 13-09-2009 Through 16-09-2009",

year = "2011",

doi = "10.1007/978-3-642-21314-4_43",

language = "English",

volume = "5778",

pages = "342--349",

journal = "Lecture Notes in Computer Science (LNCS)",

issn = "0302-9743",

publisher = "Springer Nature Link",

}

TY - JOUR

T1 - Hierarchical behaviours : getting the most bang for your bit

AU - van Dijk, S.

AU - Polani, D.

AU - Nehaniv, C.L.

N1 - “The original publication is available at www.springerlink.com” Copyright Springer

PY - 2011

Y1 - 2011

N2 - Hierarchical structuring of behaviour is prevalent in natural and artificial agents and can be shown to be useful for learning and performing tasks. To progress systematic understanding of these benefits we study the effect of hierarchical architectures on the required information processing capability of an optimally acting agent. We show that an information-theoretical approach provides important insights into why factored and layered behaviour structures are beneficial.

AB - Hierarchical structuring of behaviour is prevalent in natural and artificial agents and can be shown to be useful for learning and performing tasks. To progress systematic understanding of these benefits we study the effect of hierarchical architectures on the required information processing capability of an optimally acting agent. We show that an information-theoretical approach provides important insights into why factored and layered behaviour structures are beneficial.

U2 - 10.1007/978-3-642-21314-4_43

DO - 10.1007/978-3-642-21314-4_43

M3 - Article

SN - 0302-9743

VL - 5778

SP - 342

EP - 349

JO - Lecture Notes in Computer Science (LNCS)

JF - Lecture Notes in Computer Science (LNCS)

T2 - European Conference on Artificial Life

Y2 - 13 September 2009 through 16 September 2009

ER -

Hierarchical behaviours : getting the most bang for your bit

Abstract

Access to Document

Fingerprint

Cite this