Continuous adaptive reinforcement learning with the evolution of Self Organizing Classifiers

研究成果: 著書/レポートタイプへの貢献会議での発言

3 引用 (Scopus)

抄録

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.

元の言語英語
ホスト出版物のタイトル2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings
DOI
出版物ステータス出版済み - 2013
イベント2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Osaka, 日本
継続期間: 8 18 20138 22 2013

その他

その他2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013
日本
Osaka
期間8/18/138/22/13

Fingerprint

Reinforcement learning
Classifiers

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Human-Computer Interaction
  • Software

これを引用

Vargas, D. V., Takano, H., & Murata, J. (2013). 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 [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.

研究成果: 著書/レポートタイプへの貢献会議での発言

Vargas, DV, Takano, H & Murata, J 2013, 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., 6652558, 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013, Osaka, 日本, 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. : 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 -