loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Jose Antonio Martin H. 1 and Javier de Lope 2

Affiliations: 1 Universidad Complutense de Madrid, Spain ; 2 Universidad Politécnica de Madrid, Spain

Keyword(s): Reinforcement Learning, Multi-link Robots, Multi-Agent systems.

Related Ontology Subjects/Areas/Topics: Distributed Control Systems ; Informatics in Control, Automation and Robotics ; Intelligent Control Systems and Optimization ; Machine Learning in Control Applications ; Robot Design, Development and Control ; Robotics and Automation ; Software Agents for Intelligent Control Systems

Abstract: A distributed approach to Reinforcement Learning (RL) in multi-link robot control tasks is presented. One of the main drawbacks of classical RL is the combinatorial explosion when multiple states variables and multiple actuators are needed to optimally control a complex agent in a dynamical environment. In this paper we present an approach to avoid this drawback based on a distributed RL architecture. The experimental results in learning a control policy for diverse kind of multi-link robotic models clearly shows that it is not necessary that each individual RL-agent perceives the complete state space in order to learn a good global policy but only a reduced state space directly related to its own environmental experience. The proposed architecture combined with the use of continuous reward functions results of an impressive improvement of the learning speed making tractable some learning problems in which a classical RL with discrete rewards (-1,0,1) does not work.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.145.12.242

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Antonio Martin H., J. and de Lope, J. (2007). A DISTRIBUTED REINFORCEMENT LEARNING CONTROL ARCHITECTURE FOR MULTI-LINK ROBOTS - Experimental Validation. In Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO; ISBN 978-972-8865-82-5; ISSN 2184-2809, SciTePress, pages 192-197. DOI: 10.5220/0001621201920197

@conference{icinco07,
author={Jose {Antonio Martin H.}. and Javier {de Lope}.},
title={A DISTRIBUTED REINFORCEMENT LEARNING CONTROL ARCHITECTURE FOR MULTI-LINK ROBOTS - Experimental Validation},
booktitle={Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO},
year={2007},
pages={192-197},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001621201920197},
isbn={978-972-8865-82-5},
issn={2184-2809},
}

TY - CONF

JO - Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO
TI - A DISTRIBUTED REINFORCEMENT LEARNING CONTROL ARCHITECTURE FOR MULTI-LINK ROBOTS - Experimental Validation
SN - 978-972-8865-82-5
IS - 2184-2809
AU - Antonio Martin H., J.
AU - de Lope, J.
PY - 2007
SP - 192
EP - 197
DO - 10.5220/0001621201920197
PB - SciTePress

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic