Multi-dimensional reinforcement learning using a vector Q-net - Application to mobile robots

Kazuo Kiguchi, Thrishantha Nanayakkara, Keigo Watanabe, Toshio Fukuda

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Reinforcement learning is considered as an important tool for robotic learning in unknown/uncertain environments. In this paper, we propose an evaluation function expressed in a vector form to realize multi-dimensional reinforcement learning. The novel feature of the proposed method is that learning one behavior induces parallel learning of other behaviors though the objectives of each behavior are different. In brief, all behaviors watch other behaviors from a critical point of view. Therefore, in the proposed method, there is cross-criticism and parallel learning that make the multi-dimensional learning process more efficient. By applying the proposed learning method, we carried out multi-dimensional evaluation (reward) and multi-dimensional learning simultaneously in one trial. A special neural network (Q-net), in which the weights and the output are represented by vectors, is proposed to realize a critic network for Q-learning. The proposed learning method is applied for behavior planning of mobile robots.

Original languageEnglish
Pages (from-to)142-148
Number of pages7
JournalInternational Journal of Control, Automation and Systems
Volume1
Issue number1
Publication statusPublished - Jan 1 2003
Externally publishedYes

Fingerprint

Reinforcement learning
Mobile robots
Function evaluation
Robotics
Neural networks
Planning

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science Applications

Cite this

Multi-dimensional reinforcement learning using a vector Q-net - Application to mobile robots. / Kiguchi, Kazuo; Nanayakkara, Thrishantha; Watanabe, Keigo; Fukuda, Toshio.

In: International Journal of Control, Automation and Systems, Vol. 1, No. 1, 01.01.2003, p. 142-148.

Research output: Contribution to journalArticle

Kiguchi, Kazuo ; Nanayakkara, Thrishantha ; Watanabe, Keigo ; Fukuda, Toshio. / Multi-dimensional reinforcement learning using a vector Q-net - Application to mobile robots. In: International Journal of Control, Automation and Systems. 2003 ; Vol. 1, No. 1. pp. 142-148.
@article{708ddc965d044b14ad80f16199cc82b5,
title = "Multi-dimensional reinforcement learning using a vector Q-net - Application to mobile robots",
abstract = "Reinforcement learning is considered as an important tool for robotic learning in unknown/uncertain environments. In this paper, we propose an evaluation function expressed in a vector form to realize multi-dimensional reinforcement learning. The novel feature of the proposed method is that learning one behavior induces parallel learning of other behaviors though the objectives of each behavior are different. In brief, all behaviors watch other behaviors from a critical point of view. Therefore, in the proposed method, there is cross-criticism and parallel learning that make the multi-dimensional learning process more efficient. By applying the proposed learning method, we carried out multi-dimensional evaluation (reward) and multi-dimensional learning simultaneously in one trial. A special neural network (Q-net), in which the weights and the output are represented by vectors, is proposed to realize a critic network for Q-learning. The proposed learning method is applied for behavior planning of mobile robots.",
author = "Kazuo Kiguchi and Thrishantha Nanayakkara and Keigo Watanabe and Toshio Fukuda",
year = "2003",
month = "1",
day = "1",
language = "English",
volume = "1",
pages = "142--148",
journal = "International Journal of Control, Automation and Systems",
issn = "1598-6446",
publisher = "Institute of Control, Robotics and Systems",
number = "1",

}

TY - JOUR

T1 - Multi-dimensional reinforcement learning using a vector Q-net - Application to mobile robots

AU - Kiguchi, Kazuo

AU - Nanayakkara, Thrishantha

AU - Watanabe, Keigo

AU - Fukuda, Toshio

PY - 2003/1/1

Y1 - 2003/1/1

N2 - Reinforcement learning is considered as an important tool for robotic learning in unknown/uncertain environments. In this paper, we propose an evaluation function expressed in a vector form to realize multi-dimensional reinforcement learning. The novel feature of the proposed method is that learning one behavior induces parallel learning of other behaviors though the objectives of each behavior are different. In brief, all behaviors watch other behaviors from a critical point of view. Therefore, in the proposed method, there is cross-criticism and parallel learning that make the multi-dimensional learning process more efficient. By applying the proposed learning method, we carried out multi-dimensional evaluation (reward) and multi-dimensional learning simultaneously in one trial. A special neural network (Q-net), in which the weights and the output are represented by vectors, is proposed to realize a critic network for Q-learning. The proposed learning method is applied for behavior planning of mobile robots.

AB - Reinforcement learning is considered as an important tool for robotic learning in unknown/uncertain environments. In this paper, we propose an evaluation function expressed in a vector form to realize multi-dimensional reinforcement learning. The novel feature of the proposed method is that learning one behavior induces parallel learning of other behaviors though the objectives of each behavior are different. In brief, all behaviors watch other behaviors from a critical point of view. Therefore, in the proposed method, there is cross-criticism and parallel learning that make the multi-dimensional learning process more efficient. By applying the proposed learning method, we carried out multi-dimensional evaluation (reward) and multi-dimensional learning simultaneously in one trial. A special neural network (Q-net), in which the weights and the output are represented by vectors, is proposed to realize a critic network for Q-learning. The proposed learning method is applied for behavior planning of mobile robots.

UR - http://www.scopus.com/inward/record.url?scp=4544348159&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4544348159&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:4544348159

VL - 1

SP - 142

EP - 148

JO - International Journal of Control, Automation and Systems

JF - International Journal of Control, Automation and Systems

SN - 1598-6446

IS - 1

ER -