Continuous adaptive reinforcement learning with the evolution of Self Organizing Classifiers

Danilo Vasconcellos Vargas; Hirotaka Takano; Junichi Murata

doi:10.1109/DevLrn.2013.6652558

Continuous adaptive reinforcement learning with the evolution of Self Organizing Classifiers

Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata

研究成果: 書籍/レポートタイプへの寄稿 › 会議への寄与

3 被引用数 (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.

本文言語	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	https://doi.org/10.1109/DevLrn.2013.6652558
出版ステータス	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月 18 2013 → 8月 22 2013

その他

その他	2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013
国/地域	日本
City	Osaka
Period	8/18/13 → 8/22/13

!!!All Science Journal Classification (ASJC) codes

人工知能
人間とコンピュータの相互作用
ソフトウェア

文献へのアクセス

10.1109/DevLrn.2013.6652558

他のファイルとリンク

引用スタイル

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: 書籍/レポートタイプへの寄稿 › 会議への寄与

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, 日本, 8/18/13. https://doi.org/10.1109/DevLrn.2013.6652558

@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",

note = "2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 ; Conference date: 18-08-2013 Through 22-08-2013",

}

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

AN - SCOPUS:84891122041

SN - 9781479910366

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

T2 - 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013

Y2 - 18 August 2013 through 22 August 2013

ER -

Continuous adaptive reinforcement learning with the evolution of Self Organizing Classifiers

抄録

その他

!!!All Science Journal Classification (ASJC) codes

文献へのアクセス

他のファイルとリンク

フィンガープリント

引用スタイル