A phased reinforcement learning algorithm for complex control problems

Takakuni Goto; Noriyasu Homma; Makoto Yoshizawa; Kenichi Abe

doi:10.1007/s10015-007-0427-y

A phased reinforcement learning algorithm for complex control problems

Takakuni Goto, Noriyasu Homma, Makoto Yoshizawa, Kenichi Abe

Research output: Contribution to journal › Article › peer-review

6 Citations (Scopus)

Abstract

In this article, a phased reinforcement learning algorithm for controlling complex systems is proposed. The key element of the proposed algorithm is a shaping function defined on a novel position-direction space. The shaping function is autonomously constructed once the goal is reached, and constrains the exploration area to optimize the policy. The efficiency of the proposed shaping function was demonstrated by using a complex control problem of positioning a 2-link planar underactuated manipulator.

Original language	English
Pages (from-to)	190-196
Number of pages	7
Journal	Artificial Life and Robotics
Volume	11
Issue number	2
DOIs	https://doi.org/10.1007/s10015-007-0427-y
Publication status	Published - 2007 Jul

Keywords

Human exploration-exploitation strategy
Promising zone
Reinforcement learning
Shaping function

ASJC Scopus subject areas

Biochemistry, Genetics and Molecular Biology(all)
Artificial Intelligence

Access to Document

10.1007/s10015-007-0427-y

Cite this

@article{89794b98a4ef4db390244d347f884070,

title = "A phased reinforcement learning algorithm for complex control problems",

abstract = "In this article, a phased reinforcement learning algorithm for controlling complex systems is proposed. The key element of the proposed algorithm is a shaping function defined on a novel position-direction space. The shaping function is autonomously constructed once the goal is reached, and constrains the exploration area to optimize the policy. The efficiency of the proposed shaping function was demonstrated by using a complex control problem of positioning a 2-link planar underactuated manipulator.",

keywords = "Human exploration-exploitation strategy, Promising zone, Reinforcement learning, Shaping function",

author = "Takakuni Goto and Noriyasu Homma and Makoto Yoshizawa and Kenichi Abe",

year = "2007",

month = jul,

doi = "10.1007/s10015-007-0427-y",

language = "English",

volume = "11",

pages = "190--196",

journal = "Artificial Life and Robotics",

issn = "1433-5298",

publisher = "Springer Japan",

number = "2",

}

TY - JOUR

T1 - A phased reinforcement learning algorithm for complex control problems

AU - Goto, Takakuni

AU - Homma, Noriyasu

AU - Yoshizawa, Makoto

AU - Abe, Kenichi

PY - 2007/7

Y1 - 2007/7

N2 - In this article, a phased reinforcement learning algorithm for controlling complex systems is proposed. The key element of the proposed algorithm is a shaping function defined on a novel position-direction space. The shaping function is autonomously constructed once the goal is reached, and constrains the exploration area to optimize the policy. The efficiency of the proposed shaping function was demonstrated by using a complex control problem of positioning a 2-link planar underactuated manipulator.

AB - In this article, a phased reinforcement learning algorithm for controlling complex systems is proposed. The key element of the proposed algorithm is a shaping function defined on a novel position-direction space. The shaping function is autonomously constructed once the goal is reached, and constrains the exploration area to optimize the policy. The efficiency of the proposed shaping function was demonstrated by using a complex control problem of positioning a 2-link planar underactuated manipulator.

KW - Human exploration-exploitation strategy

KW - Promising zone

KW - Reinforcement learning

KW - Shaping function

UR - http://www.scopus.com/inward/record.url?scp=34547938723&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547938723&partnerID=8YFLogxK

U2 - 10.1007/s10015-007-0427-y

DO - 10.1007/s10015-007-0427-y

M3 - Article

AN - SCOPUS:34547938723

VL - 11

SP - 190

EP - 196

JO - Artificial Life and Robotics

JF - Artificial Life and Robotics

SN - 1433-5298

IS - 2

ER -

A phased reinforcement learning algorithm for complex control problems

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this