A new approach for supervised learning based influence value reinforcement learning

André Valdivia; Jose Alfredo Herrera Quispe; Dennis Barrios-Aranibar

doi:10.1145/3184066.3184094

A new approach for supervised learning based influence value reinforcement learning

André Valdivia, Jose Alfredo Herrera Quispe, Dennis Barrios-Aranibar

Departamento Académico de Ingeniería de Sistemas e Informática

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The neural self-organization, is an innate feature of the mammal's brains, and is necessary for its operation. The most known neuronal models that use this characteristic are the self-organized maps (SOM) and the adaptive resonance theory (ART), but those models, did not take the neuron as a processing unit, as the biological counterpart. On the other hand, the influence value learning paradigm [1], used in multi-agent environments, proof that agents can communicate with each other [2]; and they can self-organize to assign tasks; without any interference. Motivated by this missing feature in artificial networks, and with the influence value reinforcement learning algorithm; a new approach to supervised learning was modeled using the neuron as an agent learning by reinforcement.

Original language	English
Title of host publication	2nd International Conference on Machine Learning and Soft Computing, ICMLSC 2018
Publisher	Association for Computing Machinery
Pages	24-28
Number of pages	5
ISBN (Electronic)	9781450363365
DOIs	https://doi.org/10.1145/3184066.3184094
State	Published - 2 Feb 2018
Event	2nd International Conference on Machine Learning and Soft Computing, ICMLSC 2018 - Phu Quoc Island, Viet Nam Duration: 2 Feb 2018 → 4 Feb 2018

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	2nd International Conference on Machine Learning and Soft Computing, ICMLSC 2018
Country/Territory	Viet Nam
City	Phu Quoc Island
Period	2/02/18 → 4/02/18

Bibliographical note

Publisher Copyright:
© Association for Computing Machinery. All rights reserved.

Keywords

Multi-agent
Neural networks
Reinforcement learning

Access to Document

10.1145/3184066.3184094

Cite this

Valdivia, A., Herrera Quispe, J. A., & Barrios-Aranibar, D. (2018). A new approach for supervised learning based influence value reinforcement learning. In 2nd International Conference on Machine Learning and Soft Computing, ICMLSC 2018 (pp. 24-28). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3184066.3184094

@inproceedings{f7663e094c44476e9ba1090d0ba7d301,

title = "A new approach for supervised learning based influence value reinforcement learning",

abstract = "The neural self-organization, is an innate feature of the mammal's brains, and is necessary for its operation. The most known neuronal models that use this characteristic are the self-organized maps (SOM) and the adaptive resonance theory (ART), but those models, did not take the neuron as a processing unit, as the biological counterpart. On the other hand, the influence value learning paradigm [1], used in multi-agent environments, proof that agents can communicate with each other [2]; and they can self-organize to assign tasks; without any interference. Motivated by this missing feature in artificial networks, and with the influence value reinforcement learning algorithm; a new approach to supervised learning was modeled using the neuron as an agent learning by reinforcement.",

keywords = "Multi-agent, Neural networks, Reinforcement learning",

author = "Andr{\'e} Valdivia and {Herrera Quispe}, {Jose Alfredo} and Dennis Barrios-Aranibar",

year = "2018",

month = feb,

day = "2",

doi = "10.1145/3184066.3184094",

language = "Ingl{\'e}s",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "24--28",

booktitle = "2nd International Conference on Machine Learning and Soft Computing, ICMLSC 2018",

}

Valdivia, A, Herrera Quispe, JA & Barrios-Aranibar, D 2018, A new approach for supervised learning based influence value reinforcement learning. in 2nd International Conference on Machine Learning and Soft Computing, ICMLSC 2018. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 24-28, 2nd International Conference on Machine Learning and Soft Computing, ICMLSC 2018, Phu Quoc Island, Viet Nam, 2/02/18. https://doi.org/10.1145/3184066.3184094

A new approach for supervised learning based influence value reinforcement learning. / Valdivia, André; Herrera Quispe, Jose Alfredo; Barrios-Aranibar, Dennis.

2nd International Conference on Machine Learning and Soft Computing, ICMLSC 2018. Association for Computing Machinery, 2018. p. 24-28 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A new approach for supervised learning based influence value reinforcement learning

AU - Valdivia, André

AU - Herrera Quispe, Jose Alfredo

AU - Barrios-Aranibar, Dennis

PY - 2018/2/2

Y1 - 2018/2/2

N2 - The neural self-organization, is an innate feature of the mammal's brains, and is necessary for its operation. The most known neuronal models that use this characteristic are the self-organized maps (SOM) and the adaptive resonance theory (ART), but those models, did not take the neuron as a processing unit, as the biological counterpart. On the other hand, the influence value learning paradigm [1], used in multi-agent environments, proof that agents can communicate with each other [2]; and they can self-organize to assign tasks; without any interference. Motivated by this missing feature in artificial networks, and with the influence value reinforcement learning algorithm; a new approach to supervised learning was modeled using the neuron as an agent learning by reinforcement.

AB - The neural self-organization, is an innate feature of the mammal's brains, and is necessary for its operation. The most known neuronal models that use this characteristic are the self-organized maps (SOM) and the adaptive resonance theory (ART), but those models, did not take the neuron as a processing unit, as the biological counterpart. On the other hand, the influence value learning paradigm [1], used in multi-agent environments, proof that agents can communicate with each other [2]; and they can self-organize to assign tasks; without any interference. Motivated by this missing feature in artificial networks, and with the influence value reinforcement learning algorithm; a new approach to supervised learning was modeled using the neuron as an agent learning by reinforcement.

KW - Multi-agent

KW - Neural networks

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=85060432650&partnerID=8YFLogxK

U2 - 10.1145/3184066.3184094

DO - 10.1145/3184066.3184094

M3 - Contribución a la conferencia

AN - SCOPUS:85060432650

T3 - ACM International Conference Proceeding Series

SP - 24

EP - 28

BT - 2nd International Conference on Machine Learning and Soft Computing, ICMLSC 2018

PB - Association for Computing Machinery

Y2 - 2 February 2018 through 4 February 2018

ER -

A new approach for supervised learning based influence value reinforcement learning

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this