Behavior Acquisition on a Mobile Robot Using Reinforcement Learning with Continuous State Space

Tomoyuki Arai; Yuichiro Toda; Naoyuki Kubota

doi:10.1109/ICMLC48188.2019.8949181

Behavior Acquisition on a Mobile Robot Using Reinforcement Learning with Continuous State Space

Tomoyuki Arai, Yuichiro Toda, Naoyuki Kubota

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

Abstract

In the application of Reinforcement Learning to real tasks, the construction of state space is a significant problem. In order to use in the real-world environment, we need to deal with the problem of continuous information. Therefore, we proposed a method of the construction of state space using Growing Neural Gas. In our method, the agent constructs a state space model from its own experience autonomously. Furthermore, it can reconstruct the suitable state space model to adapt the complication of the environment. Through the experiments, we showed that Reinforcement Learning could be performed efficiently by successively updating the state space model according to the environment.

Original language	English
Title of host publication	Proceedings of 2019 International Conference on Machine Learning and Cybernetics, ICMLC 2019
Publisher	IEEE Computer Society
ISBN (Electronic)	9781728128160
DOIs	https://doi.org/10.1109/ICMLC48188.2019.8949181
Publication status	Published - Jul 2019
Event	18th International Conference on Machine Learning and Cybernetics, ICMLC 2019 - Kobe, Japan Duration: Jul 7 2019 → Jul 10 2019

Publication series

Name	Proceedings - International Conference on Machine Learning and Cybernetics
Volume	2019-July
ISSN (Print)	2160-133X
ISSN (Electronic)	2160-1348

Conference

Conference	18th International Conference on Machine Learning and Cybernetics, ICMLC 2019
Country	Japan
City	Kobe
Period	7/7/19 → 7/10/19

Keywords

Machine learning
Mobile robot
Reinforcement learning
Self-Organization
State space

ASJC Scopus subject areas

Artificial Intelligence
Computational Theory and Mathematics
Computer Networks and Communications
Human-Computer Interaction

Access to Document

10.1109/ICMLC48188.2019.8949181

Fingerprint Dive into the research topics of 'Behavior Acquisition on a Mobile Robot Using Reinforcement Learning with Continuous State Space'. Together they form a unique fingerprint.

Cite this

Arai, T., Toda, Y., & Kubota, N. (2019). Behavior Acquisition on a Mobile Robot Using Reinforcement Learning with Continuous State Space. In Proceedings of 2019 International Conference on Machine Learning and Cybernetics, ICMLC 2019 [8949181] (Proceedings - International Conference on Machine Learning and Cybernetics; Vol. 2019-July). IEEE Computer Society. https://doi.org/10.1109/ICMLC48188.2019.8949181

Behavior Acquisition on a Mobile Robot Using Reinforcement Learning with Continuous State Space. / Arai, Tomoyuki; Toda, Yuichiro; Kubota, Naoyuki.

Proceedings of 2019 International Conference on Machine Learning and Cybernetics, ICMLC 2019. IEEE Computer Society, 2019. 8949181 (Proceedings - International Conference on Machine Learning and Cybernetics; Vol. 2019-July).

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

Arai, T, Toda, Y & Kubota, N 2019, Behavior Acquisition on a Mobile Robot Using Reinforcement Learning with Continuous State Space. in Proceedings of 2019 International Conference on Machine Learning and Cybernetics, ICMLC 2019., 8949181, Proceedings - International Conference on Machine Learning and Cybernetics, vol. 2019-July, IEEE Computer Society, 18th International Conference on Machine Learning and Cybernetics, ICMLC 2019, Kobe, Japan, 7/7/19. https://doi.org/10.1109/ICMLC48188.2019.8949181

Arai T, Toda Y, Kubota N. Behavior Acquisition on a Mobile Robot Using Reinforcement Learning with Continuous State Space. In Proceedings of 2019 International Conference on Machine Learning and Cybernetics, ICMLC 2019. IEEE Computer Society. 2019. 8949181. (Proceedings - International Conference on Machine Learning and Cybernetics). https://doi.org/10.1109/ICMLC48188.2019.8949181

@inproceedings{a1c43fa6711744dbb80e5930e23668da,

title = "Behavior Acquisition on a Mobile Robot Using Reinforcement Learning with Continuous State Space",

abstract = "In the application of Reinforcement Learning to real tasks, the construction of state space is a significant problem. In order to use in the real-world environment, we need to deal with the problem of continuous information. Therefore, we proposed a method of the construction of state space using Growing Neural Gas. In our method, the agent constructs a state space model from its own experience autonomously. Furthermore, it can reconstruct the suitable state space model to adapt the complication of the environment. Through the experiments, we showed that Reinforcement Learning could be performed efficiently by successively updating the state space model according to the environment.",

keywords = "Machine learning, Mobile robot, Reinforcement learning, Self-Organization, State space",

author = "Tomoyuki Arai and Yuichiro Toda and Naoyuki Kubota",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; 18th International Conference on Machine Learning and Cybernetics, ICMLC 2019 ; Conference date: 07-07-2019 Through 10-07-2019",

year = "2019",

month = jul,

doi = "10.1109/ICMLC48188.2019.8949181",

language = "English",

series = "Proceedings - International Conference on Machine Learning and Cybernetics",

publisher = "IEEE Computer Society",

booktitle = "Proceedings of 2019 International Conference on Machine Learning and Cybernetics, ICMLC 2019",

address = "United States",

}

TY - GEN

T1 - Behavior Acquisition on a Mobile Robot Using Reinforcement Learning with Continuous State Space

AU - Arai, Tomoyuki

AU - Toda, Yuichiro

AU - Kubota, Naoyuki

PY - 2019/7

Y1 - 2019/7

N2 - In the application of Reinforcement Learning to real tasks, the construction of state space is a significant problem. In order to use in the real-world environment, we need to deal with the problem of continuous information. Therefore, we proposed a method of the construction of state space using Growing Neural Gas. In our method, the agent constructs a state space model from its own experience autonomously. Furthermore, it can reconstruct the suitable state space model to adapt the complication of the environment. Through the experiments, we showed that Reinforcement Learning could be performed efficiently by successively updating the state space model according to the environment.

AB - In the application of Reinforcement Learning to real tasks, the construction of state space is a significant problem. In order to use in the real-world environment, we need to deal with the problem of continuous information. Therefore, we proposed a method of the construction of state space using Growing Neural Gas. In our method, the agent constructs a state space model from its own experience autonomously. Furthermore, it can reconstruct the suitable state space model to adapt the complication of the environment. Through the experiments, we showed that Reinforcement Learning could be performed efficiently by successively updating the state space model according to the environment.

KW - Machine learning

KW - Mobile robot

KW - Reinforcement learning

KW - Self-Organization

KW - State space

UR - http://www.scopus.com/inward/record.url?scp=85078528811&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85078528811&partnerID=8YFLogxK

U2 - 10.1109/ICMLC48188.2019.8949181

DO - 10.1109/ICMLC48188.2019.8949181

M3 - Conference contribution

AN - SCOPUS:85078528811

T3 - Proceedings - International Conference on Machine Learning and Cybernetics

BT - Proceedings of 2019 International Conference on Machine Learning and Cybernetics, ICMLC 2019

PB - IEEE Computer Society

T2 - 18th International Conference on Machine Learning and Cybernetics, ICMLC 2019

Y2 - 7 July 2019 through 10 July 2019

ER -