Continuous adaptive reinforcement learning with the evolution of Self Organizing Classifiers

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Learning classifier systems have been solving reinforcement learning problems for some time. However, they face difficulties under multi-step continuous problems. Adaptation may also become harder with time since the convergence of the population decreases its diversity. This article demonstrate that the novel Self Organizing Classifiers method can cope with dynamical multi-step continuous problems. Moreover, adaptation remains the same after convergence.

Original languageEnglish
Title of host publication2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings
DOIs
Publication statusPublished - 2013
Event2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Osaka, Japan
Duration: Aug 18 2013Aug 22 2013

Other

Other2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013
CountryJapan
CityOsaka
Period8/18/138/22/13

Fingerprint

Reinforcement learning
Classifiers

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Human-Computer Interaction
  • Software

Cite this

Vargas, D. V., Takano, H., & Murata, J. (2013). Continuous adaptive reinforcement learning with the evolution of Self Organizing Classifiers. In 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings [6652558] https://doi.org/10.1109/DevLrn.2013.6652558

Continuous adaptive reinforcement learning with the evolution of Self Organizing Classifiers. / Vargas, Danilo Vasconcellos; Takano, Hirotaka; Murata, Junichi.

2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings. 2013. 6652558.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Vargas, DV, Takano, H & Murata, J 2013, Continuous adaptive reinforcement learning with the evolution of Self Organizing Classifiers. in 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings., 6652558, 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013, Osaka, Japan, 8/18/13. https://doi.org/10.1109/DevLrn.2013.6652558
Vargas DV, Takano H, Murata J. Continuous adaptive reinforcement learning with the evolution of Self Organizing Classifiers. In 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings. 2013. 6652558 https://doi.org/10.1109/DevLrn.2013.6652558
Vargas, Danilo Vasconcellos ; Takano, Hirotaka ; Murata, Junichi. / Continuous adaptive reinforcement learning with the evolution of Self Organizing Classifiers. 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings. 2013.
@inproceedings{119d2fe924c24e9cafb50f91108aa01f,
title = "Continuous adaptive reinforcement learning with the evolution of Self Organizing Classifiers",
abstract = "Learning classifier systems have been solving reinforcement learning problems for some time. However, they face difficulties under multi-step continuous problems. Adaptation may also become harder with time since the convergence of the population decreases its diversity. This article demonstrate that the novel Self Organizing Classifiers method can cope with dynamical multi-step continuous problems. Moreover, adaptation remains the same after convergence.",
author = "Vargas, {Danilo Vasconcellos} and Hirotaka Takano and Junichi Murata",
year = "2013",
doi = "10.1109/DevLrn.2013.6652558",
language = "English",
isbn = "9781479910366",
booktitle = "2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings",

}

TY - GEN

T1 - Continuous adaptive reinforcement learning with the evolution of Self Organizing Classifiers

AU - Vargas, Danilo Vasconcellos

AU - Takano, Hirotaka

AU - Murata, Junichi

PY - 2013

Y1 - 2013

N2 - Learning classifier systems have been solving reinforcement learning problems for some time. However, they face difficulties under multi-step continuous problems. Adaptation may also become harder with time since the convergence of the population decreases its diversity. This article demonstrate that the novel Self Organizing Classifiers method can cope with dynamical multi-step continuous problems. Moreover, adaptation remains the same after convergence.

AB - Learning classifier systems have been solving reinforcement learning problems for some time. However, they face difficulties under multi-step continuous problems. Adaptation may also become harder with time since the convergence of the population decreases its diversity. This article demonstrate that the novel Self Organizing Classifiers method can cope with dynamical multi-step continuous problems. Moreover, adaptation remains the same after convergence.

UR - http://www.scopus.com/inward/record.url?scp=84891122041&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891122041&partnerID=8YFLogxK

U2 - 10.1109/DevLrn.2013.6652558

DO - 10.1109/DevLrn.2013.6652558

M3 - Conference contribution

SN - 9781479910366

BT - 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings

ER -