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

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 language	English
Title of host publication	2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings
DOIs	https://doi.org/10.1109/DevLrn.2013.6652558
Publication status	Published - 2013
Event	2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Osaka, Japan Duration: Aug 18 2013 → Aug 22 2013

Other

Other	2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013
Country	Japan
City	Osaka
Period	8/18/13 → 8/22/13

Fingerprint

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 proceeding › Conference 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

@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

AN - SCOPUS:84891122041

SN - 9781479910366

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

ER -

Access to Document

10.1109/DevLrn.2013.6652558