Multi target tracking using a compact Q-learning with a teacher

E. M. Saad; M. H. Awadalla; A. M. Hamdy; H. I. Ali

doi:10.1109/ICCES.2008.4772991

Multi target tracking using a compact Q-learning with a teacher

E. M. Saad, M. H. Awadalla, A. M. Hamdy, H. I. Ali

Electrical and Computer Engineering

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

Abstract

This paper focuses on developing a team of mobile robots capable of learning via human interaction. A modified Q-learning algorithm incorporating a teacher is proposed. The paper first concentrates on simplifying the Q-learning algorithm to be implemented on small and simple team of robots having limited capabilities of memory and computational power. Second it concentrates on the incorporation of a human teacher in the Q-learning algorithm. Experiments using the well-known robot simulator Webots on both single and multi-target tracking tasks have been conducted. The achieved results show the success of the proposed algorithm in the over all system performance.

Original language	English
Title of host publication	2008 International Conference on Computer Engineering and Systems, ICCES 2008
Pages	173-178
Number of pages	6
DOIs	https://doi.org/10.1109/ICCES.2008.4772991
Publication status	Published - 2008
Event	2008 International Conference on Computer Engineering and Systems, ICCES 2008 - Cairo, Egypt Duration: Nov 25 2008 → Nov 27 2008

Other

Other	2008 International Conference on Computer Engineering and Systems, ICCES 2008
Country/Territory	Egypt
City	Cairo
Period	11/25/08 → 11/27/08

Keywords

Human-robot interaction
Machine learning
Q-learning
Reinforcement learning

ASJC Scopus subject areas

Computer Science Applications
Hardware and Architecture
Software

Access to Document

10.1109/ICCES.2008.4772991

Cite this

@inproceedings{9953719afad64978b28516c249b58a0e,

title = "Multi target tracking using a compact Q-learning with a teacher",

abstract = "This paper focuses on developing a team of mobile robots capable of learning via human interaction. A modified Q-learning algorithm incorporating a teacher is proposed. The paper first concentrates on simplifying the Q-learning algorithm to be implemented on small and simple team of robots having limited capabilities of memory and computational power. Second it concentrates on the incorporation of a human teacher in the Q-learning algorithm. Experiments using the well-known robot simulator Webots on both single and multi-target tracking tasks have been conducted. The achieved results show the success of the proposed algorithm in the over all system performance.",

keywords = "Human-robot interaction, Machine learning, Q-learning, Reinforcement learning",

author = "Saad, {E. M.} and Awadalla, {M. H.} and Hamdy, {A. M.} and Ali, {H. I.}",

year = "2008",

doi = "10.1109/ICCES.2008.4772991",

language = "English",

isbn = "9781424421152",

pages = "173--178",

booktitle = "2008 International Conference on Computer Engineering and Systems, ICCES 2008",

note = "2008 International Conference on Computer Engineering and Systems, ICCES 2008 ; Conference date: 25-11-2008 Through 27-11-2008",

}

TY - GEN

T1 - Multi target tracking using a compact Q-learning with a teacher

AU - Saad, E. M.

AU - Awadalla, M. H.

AU - Hamdy, A. M.

AU - Ali, H. I.

PY - 2008

Y1 - 2008

N2 - This paper focuses on developing a team of mobile robots capable of learning via human interaction. A modified Q-learning algorithm incorporating a teacher is proposed. The paper first concentrates on simplifying the Q-learning algorithm to be implemented on small and simple team of robots having limited capabilities of memory and computational power. Second it concentrates on the incorporation of a human teacher in the Q-learning algorithm. Experiments using the well-known robot simulator Webots on both single and multi-target tracking tasks have been conducted. The achieved results show the success of the proposed algorithm in the over all system performance.

AB - This paper focuses on developing a team of mobile robots capable of learning via human interaction. A modified Q-learning algorithm incorporating a teacher is proposed. The paper first concentrates on simplifying the Q-learning algorithm to be implemented on small and simple team of robots having limited capabilities of memory and computational power. Second it concentrates on the incorporation of a human teacher in the Q-learning algorithm. Experiments using the well-known robot simulator Webots on both single and multi-target tracking tasks have been conducted. The achieved results show the success of the proposed algorithm in the over all system performance.

KW - Human-robot interaction

KW - Machine learning

KW - Q-learning

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=67649544245&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67649544245&partnerID=8YFLogxK

U2 - 10.1109/ICCES.2008.4772991

DO - 10.1109/ICCES.2008.4772991

M3 - Conference contribution

AN - SCOPUS:67649544245

SN - 9781424421152

SP - 173

EP - 178

BT - 2008 International Conference on Computer Engineering and Systems, ICCES 2008

T2 - 2008 International Conference on Computer Engineering and Systems, ICCES 2008

Y2 - 25 November 2008 through 27 November 2008

ER -

Multi target tracking using a compact Q-learning with a teacher

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this