Cargando…
Learning modular policies for robotics
A promising idea for scaling robot learning to more complex tasks is to use elemental behaviors as building blocks to compose more complex behavior. Ideally, such building blocks are used in combination with a learning algorithm that is able to learn to select, adapt, sequence and co-activate the bu...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2014
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4052508/ https://www.ncbi.nlm.nih.gov/pubmed/24966830 http://dx.doi.org/10.3389/fncom.2014.00062 |
_version_ | 1782320244420771840 |
---|---|
author | Neumann, Gerhard Daniel, Christian Paraschos, Alexandros Kupcsik, Andras Peters, Jan |
author_facet | Neumann, Gerhard Daniel, Christian Paraschos, Alexandros Kupcsik, Andras Peters, Jan |
author_sort | Neumann, Gerhard |
collection | PubMed |
description | A promising idea for scaling robot learning to more complex tasks is to use elemental behaviors as building blocks to compose more complex behavior. Ideally, such building blocks are used in combination with a learning algorithm that is able to learn to select, adapt, sequence and co-activate the building blocks. While there has been a lot of work on approaches that support one of these requirements, no learning algorithm exists that unifies all these properties in one framework. In this paper we present our work on a unified approach for learning such a modular control architecture. We introduce new policy search algorithms that are based on information-theoretic principles and are able to learn to select, adapt and sequence the building blocks. Furthermore, we developed a new representation for the individual building block that supports co-activation and principled ways for adapting the movement. Finally, we summarize our experiments for learning modular control architectures in simulation and with real robots. |
format | Online Article Text |
id | pubmed-4052508 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2014 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-40525082014-06-25 Learning modular policies for robotics Neumann, Gerhard Daniel, Christian Paraschos, Alexandros Kupcsik, Andras Peters, Jan Front Comput Neurosci Neuroscience A promising idea for scaling robot learning to more complex tasks is to use elemental behaviors as building blocks to compose more complex behavior. Ideally, such building blocks are used in combination with a learning algorithm that is able to learn to select, adapt, sequence and co-activate the building blocks. While there has been a lot of work on approaches that support one of these requirements, no learning algorithm exists that unifies all these properties in one framework. In this paper we present our work on a unified approach for learning such a modular control architecture. We introduce new policy search algorithms that are based on information-theoretic principles and are able to learn to select, adapt and sequence the building blocks. Furthermore, we developed a new representation for the individual building block that supports co-activation and principled ways for adapting the movement. Finally, we summarize our experiments for learning modular control architectures in simulation and with real robots. Frontiers Media S.A. 2014-06-11 /pmc/articles/PMC4052508/ /pubmed/24966830 http://dx.doi.org/10.3389/fncom.2014.00062 Text en Copyright © 2014 Neumann, Daniel, Paraschos, Kupcsik and Peters. http://creativecommons.org/licenses/by/3.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Neuroscience Neumann, Gerhard Daniel, Christian Paraschos, Alexandros Kupcsik, Andras Peters, Jan Learning modular policies for robotics |
title | Learning modular policies for robotics |
title_full | Learning modular policies for robotics |
title_fullStr | Learning modular policies for robotics |
title_full_unstemmed | Learning modular policies for robotics |
title_short | Learning modular policies for robotics |
title_sort | learning modular policies for robotics |
topic | Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4052508/ https://www.ncbi.nlm.nih.gov/pubmed/24966830 http://dx.doi.org/10.3389/fncom.2014.00062 |
work_keys_str_mv | AT neumanngerhard learningmodularpoliciesforrobotics AT danielchristian learningmodularpoliciesforrobotics AT paraschosalexandros learningmodularpoliciesforrobotics AT kupcsikandras learningmodularpoliciesforrobotics AT petersjan learningmodularpoliciesforrobotics |