loading
Papers

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Alejandro Agostini and Enric Celaya

Affiliation: Institut de Robòtica i Informàtica Industrial, Spain

ISBN: 978-989-8425-00-3

Keyword(s): Machine Learning in control applications, Reinforcement learning.

Related Ontology Subjects/Areas/Topics: Informatics in Control, Automation and Robotics ; Intelligent Control Systems and Optimization ; Machine Learning in Control Applications

Abstract: The successful application of Reinforcement Learning (RL) techniques to robot control is limited by the fact that, in most robotic tasks, the state and action spaces are continuous, multidimensional, and in essence, too large for conventional RL algorithms to work. The well known curse of dimensionality makes infeasible using a tabular representation of the value function, which is the classical approach that provides convergence guarantees. When a function approximation technique is used to generalize among similar states, the convergence of the algorithm is compromised, since updates unavoidably affect an extended region of the domain, that is, some situations are modified in a way that has not been really experienced, and the update may degrade the approximation. We propose a RL algorithm that uses a probability density estimation in the joint space of states, actions and $Q$-values as a means of function approximation. This allows us to devise an updating approach that, taking in to account the local sampling density, avoids an excessive modification of the approximation far from the observed sample. (More)

PDF ImageFull Text

Download
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 34.225.194.144

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:
Agostini A.; Celaya E. and (2010). REINFORCEMENT LEARNING FOR ROBOT CONTROL USING PROBABILITY DENSITY ESTIMATIONS.In Proceedings of the 7th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-8425-00-3, pages 160-168. DOI: 10.5220/0002949601600168

@conference{icinco10,
author={Alejandro Agostini and Enric Celaya},
title={REINFORCEMENT LEARNING FOR ROBOT CONTROL USING PROBABILITY DENSITY ESTIMATIONS},
booktitle={Proceedings of the 7th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2010},
pages={160-168},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002949601600168},
isbn={978-989-8425-00-3},
}

TY - CONF

JO - Proceedings of the 7th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - REINFORCEMENT LEARNING FOR ROBOT CONTROL USING PROBABILITY DENSITY ESTIMATIONS
SN - 978-989-8425-00-3
AU - Agostini, A.
AU - Celaya, E.
PY - 2010
SP - 160
EP - 168
DO - 10.5220/0002949601600168

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.