Intuitive Action Set Formation in Learning Classifier Systems with Memory Registers

L.F. Simões; M.C. Schut; E.W. Haasdijk

doi:10.3233/978-1-58603-891-5-761

Intuitive Action Set Formation in Learning Classifier Systems with Memory Registers

L.F. Simões, M.C. Schut, E.W. Haasdijk

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

Abstract

An important design goal in Learning Classifier Systems (LCS) is to equally reinforce those classifiers which cause the level of reward supplied by the environment. In this paper, we propose a new method for action set formation in LCS. When applied to a Zeroth Level Classifier System with Memory registers (ZCSM), our method allows the distribution of rewards among classifiers which result in the same memory state, rather than those encoding the same memory update action.

Original language	English
Pages (from-to)	761-762
Journal	Frontiers in Artificial Intelligence and Applications
Volume	178
DOIs	https://doi.org/10.3233/978-1-58603-891-5-761
Publication status	Published - 2008
Event	European Conference on Artificial Intelligence - Duration: 21 Jul 2008 → 25 Jul 2008

Bibliographical note

Proceedings title: Proceedings of the 18th European Conference on Artificial Intelligence (ECAI 2008)
Publisher: IOS Press
ISBN: 978-1-58603-891-5
Editors: M. Ghallab, C.D. Spyropoulos, N. Fakotakis, N. Avouris

Access to Document

10.3233/978-1-58603-891-5-761

https://www.researchgate.net/publication/220837744_Intuitive_Action_Set_Formation_in_Learning_Classifier_Systems_with_Memory_Registers

Persistent URL (handle)

Copy link address

Cite this

@article{979cc9539cec4546a9c7db2405696b24,

title = "Intuitive Action Set Formation in Learning Classifier Systems with Memory Registers",

abstract = "An important design goal in Learning Classifier Systems (LCS) is to equally reinforce those classifiers which cause the level of reward supplied by the environment. In this paper, we propose a new method for action set formation in LCS. When applied to a Zeroth Level Classifier System with Memory registers (ZCSM), our method allows the distribution of rewards among classifiers which result in the same memory state, rather than those encoding the same memory update action.",

author = "L.F. Sim{\~o}es and M.C. Schut and E.W. Haasdijk",

note = "Proceedings title: Proceedings of the 18th European Conference on Artificial Intelligence (ECAI 2008) Publisher: IOS Press ISBN: 978-1-58603-891-5 Editors: M. Ghallab, C.D. Spyropoulos, N. Fakotakis, N. Avouris; European Conference on Artificial Intelligence ; Conference date: 21-07-2008 Through 25-07-2008",

year = "2008",

doi = "10.3233/978-1-58603-891-5-761",

language = "English",

volume = "178",

pages = "761--762",

journal = "Frontiers in Artificial Intelligence and Applications",

issn = "0922-6389",

publisher = "IOS Press",

}

TY - JOUR

T1 - Intuitive Action Set Formation in Learning Classifier Systems with Memory Registers

AU - Simões, L.F.

AU - Schut, M.C.

AU - Haasdijk, E.W.

N1 - Proceedings title: Proceedings of the 18th European Conference on Artificial Intelligence (ECAI 2008) Publisher: IOS Press ISBN: 978-1-58603-891-5 Editors: M. Ghallab, C.D. Spyropoulos, N. Fakotakis, N. Avouris

PY - 2008

Y1 - 2008

N2 - An important design goal in Learning Classifier Systems (LCS) is to equally reinforce those classifiers which cause the level of reward supplied by the environment. In this paper, we propose a new method for action set formation in LCS. When applied to a Zeroth Level Classifier System with Memory registers (ZCSM), our method allows the distribution of rewards among classifiers which result in the same memory state, rather than those encoding the same memory update action.

AB - An important design goal in Learning Classifier Systems (LCS) is to equally reinforce those classifiers which cause the level of reward supplied by the environment. In this paper, we propose a new method for action set formation in LCS. When applied to a Zeroth Level Classifier System with Memory registers (ZCSM), our method allows the distribution of rewards among classifiers which result in the same memory state, rather than those encoding the same memory update action.

U2 - 10.3233/978-1-58603-891-5-761

DO - 10.3233/978-1-58603-891-5-761

M3 - Article

SN - 0922-6389

VL - 178

SP - 761

EP - 762

JO - Frontiers in Artificial Intelligence and Applications

JF - Frontiers in Artificial Intelligence and Applications

T2 - European Conference on Artificial Intelligence

Y2 - 21 July 2008 through 25 July 2008

ER -

Intuitive Action Set Formation in Learning Classifier Systems with Memory Registers

Abstract

Bibliographical note

Access to Document

Persistent URL (handle)

Fingerprint

Cite this