Learning a DFT-based sequence with reinforcement learning: a NAO implementation

The implementation of sequence learning in robotic platforms offers several challenges. Deciding when to stop one action and continue to the next requires a balance between stability of sensory information and, of course, the knowledge about what action is required next. The work presented here prop...

Full description

Bibliographic Details
Main Authors:	Durán Boris, Lee Gauss, Lowe Robert
Format:	Article
Language:	English
Published:	De Gruyter 2012-12-01
Series:	Paladyn: Journal of Behavioral Robotics
Subjects:	sequences neural dynamics reinforcement learning humanoid
Online Access:	https://doi.org/10.2478/s13230-013-0109-5

id	doaj-da529d3fad974ec992df01b2ffa31d89
record_format	Article
spelling	doaj-da529d3fad974ec992df01b2ffa31d892021-10-02T17:48:15ZengDe GruyterPaladyn: Journal of Behavioral Robotics2081-48362012-12-013418118710.2478/s13230-013-0109-5Learning a DFT-based sequence with reinforcement learning: a NAO implementationDurán Boris0Lee Gauss1Lowe Robert2 Interaction Lab University of Skövde Skövde, Sweden Interaction Lab University of Skövde Skövde, Sweden Interaction Lab University of Skövde Skövde, SwedenThe implementation of sequence learning in robotic platforms offers several challenges. Deciding when to stop one action and continue to the next requires a balance between stability of sensory information and, of course, the knowledge about what action is required next. The work presented here proposes a starting point for the successful execution and learning of dynamic sequences. Making use of the NAO humanoid platform we propose a mathematical model based on dynamic field theory and reinforcement learning methods for obtaining and performing a sequence of elementary motor behaviors. Results from the comparison of two reinforcement learning methods applied to sequence generation, for both simulation and implementation, are provided.https://doi.org/10.2478/s13230-013-0109-5sequencesneural dynamicsreinforcement learninghumanoid
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Durán Boris Lee Gauss Lowe Robert
spellingShingle	Durán Boris Lee Gauss Lowe Robert Learning a DFT-based sequence with reinforcement learning: a NAO implementation Paladyn: Journal of Behavioral Robotics sequences neural dynamics reinforcement learning humanoid
author_facet	Durán Boris Lee Gauss Lowe Robert
author_sort	Durán Boris
title	Learning a DFT-based sequence with reinforcement learning: a NAO implementation
title_short	Learning a DFT-based sequence with reinforcement learning: a NAO implementation
title_full	Learning a DFT-based sequence with reinforcement learning: a NAO implementation
title_fullStr	Learning a DFT-based sequence with reinforcement learning: a NAO implementation
title_full_unstemmed	Learning a DFT-based sequence with reinforcement learning: a NAO implementation
title_sort	learning a dft-based sequence with reinforcement learning: a nao implementation
publisher	De Gruyter
series	Paladyn: Journal of Behavioral Robotics
issn	2081-4836
publishDate	2012-12-01
description	The implementation of sequence learning in robotic platforms offers several challenges. Deciding when to stop one action and continue to the next requires a balance between stability of sensory information and, of course, the knowledge about what action is required next. The work presented here proposes a starting point for the successful execution and learning of dynamic sequences. Making use of the NAO humanoid platform we propose a mathematical model based on dynamic field theory and reinforcement learning methods for obtaining and performing a sequence of elementary motor behaviors. Results from the comparison of two reinforcement learning methods applied to sequence generation, for both simulation and implementation, are provided.
topic	sequences neural dynamics reinforcement learning humanoid
url	https://doi.org/10.2478/s13230-013-0109-5
work_keys_str_mv	AT duranboris learningadftbasedsequencewithreinforcementlearninganaoimplementation AT leegauss learningadftbasedsequencewithreinforcementlearninganaoimplementation AT lowerobert learningadftbasedsequencewithreinforcementlearninganaoimplementation
_version_	1716850512565895168

Learning a DFT-based sequence with reinforcement learning: a NAO implementation

Similar Items