Please use this identifier to cite or link to this item:https://hdl.handle.net/20.500.12259/54371
Type of publication: research article
Type of publication (PDB): Straipsnis Clarivate Analytics Web of Science / Article in Clarivate Analytics Web of Science (S1)
Field of Science: Informatika / Informatics (N009)
Author(s): Tamošiūnaitė, Minija;Asfour, Tamim;Wörgötter, Florentin
Title: Learning to reach by reinforcement learning using a receptive field based function approximation approach with continuous actions
Is part of: Biological Cybernetics. Berlyn : Springer, Vol. 100, no. 3 (2009)
Extent: p. 249-260
Date: 2009
Keywords: Reinforcement learning;Function approximation;Robot control
Abstract: Reinforcement learning methods can be used in robotics applications especially for specific target-oriented problems, for example the reward-based recalibration of goal directed actions. To this end still relatively large and continuous state-action spaces need to be efficiently handled. The goal of this paper is, thus, to develop a novel, rather simple method which uses reinforcement learning with function approximation in conjunction with different reward-strategies for solving such problems. For the testing of our method, we use a four degree-of-freedom reaching problem in 3D-space simulated by a two-joint robot arm system with two DOF each. Function approximation is based on 4D, overlapping kernels (receptive fields) and the state-action space contains about 10,000 of these. Different types of reward structures are being compared, for example, reward-on- touching-only against reward-on-approach. Furthermore, forbidden joint configurations are punished. A continuous action space is used. In spite of a rather large number of states and the continuous action space these reward/punishment strategies allow the system to find a good solution usually within about 20 trials. The efficiency of our method demonstrated in this test scenario suggests that it might be possible to use it on a real robot for problems where mixed rewards can be defined in situations where other types of learning might be difficult
Internet: https://doi.org/10.1007/s00422-009-0295-8
Affiliation(s): Informatikos fakultetas
Vytauto Didžiojo universitetas
Appears in Collections:Universiteto mokslo publikacijos / University Research Publications

Files in This Item:
marc.xml10.65 kBXMLView/Open

MARC21 XML metadata

Show full item record
Export via OAI-PMH Interface in XML Formats
Export to Other Non-XML Formats


CORE Recommender

WEB OF SCIENCETM
Citations 5

6
checked on Apr 24, 2021

Page view(s)

80
checked on May 1, 2021

Download(s)

8
checked on May 1, 2021

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.