Learning Intuitive Physics and One-Shot Imitation Using State-Action-Prediction Self-Organizing Maps

Human learning and intelligence work differently from the supervised pattern recognition approach adopted in most deep learning architectures. Humans seem to learn rich representations by exploration and imitation, build causal models of the world, and use both to flexibly solve new tasks. We sugges...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Martin Stetter, Elmar W. Lang
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi Limited 2021
Materias:	Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/26375a49689c4365acbf01ed5850008d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:26375a49689c4365acbf01ed5850008d
record_format	dspace
spelling	oai:doaj.org-article:26375a49689c4365acbf01ed5850008d2021-11-22T01:09:59ZLearning Intuitive Physics and One-Shot Imitation Using State-Action-Prediction Self-Organizing Maps1687-527310.1155/2021/5590445https://doaj.org/article/26375a49689c4365acbf01ed5850008d2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/5590445https://doaj.org/toc/1687-5273Human learning and intelligence work differently from the supervised pattern recognition approach adopted in most deep learning architectures. Humans seem to learn rich representations by exploration and imitation, build causal models of the world, and use both to flexibly solve new tasks. We suggest a simple but effective unsupervised model which develops such characteristics. The agent learns to represent the dynamical physical properties of its environment by intrinsically motivated exploration and performs inference on this representation to reach goals. For this, a set of self-organizing maps which represent state-action pairs is combined with a causal model for sequence prediction. The proposed system is evaluated in the cartpole environment. After an initial phase of playful exploration, the agent can execute kinematic simulations of the environment’s future and use those for action planning. We demonstrate its performance on a set of several related, but different one-shot imitation tasks, which the agent flexibly solves in an active inference style.Martin StetterElmar W. LangHindawi LimitedarticleComputer applications to medicine. Medical informaticsR858-859.7Neurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENComputational Intelligence and Neuroscience, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Martin Stetter Elmar W. Lang Learning Intuitive Physics and One-Shot Imitation Using State-Action-Prediction Self-Organizing Maps
description	Human learning and intelligence work differently from the supervised pattern recognition approach adopted in most deep learning architectures. Humans seem to learn rich representations by exploration and imitation, build causal models of the world, and use both to flexibly solve new tasks. We suggest a simple but effective unsupervised model which develops such characteristics. The agent learns to represent the dynamical physical properties of its environment by intrinsically motivated exploration and performs inference on this representation to reach goals. For this, a set of self-organizing maps which represent state-action pairs is combined with a causal model for sequence prediction. The proposed system is evaluated in the cartpole environment. After an initial phase of playful exploration, the agent can execute kinematic simulations of the environment’s future and use those for action planning. We demonstrate its performance on a set of several related, but different one-shot imitation tasks, which the agent flexibly solves in an active inference style.
format	article
author	Martin Stetter Elmar W. Lang
author_facet	Martin Stetter Elmar W. Lang
author_sort	Martin Stetter
title	Learning Intuitive Physics and One-Shot Imitation Using State-Action-Prediction Self-Organizing Maps
title_short	Learning Intuitive Physics and One-Shot Imitation Using State-Action-Prediction Self-Organizing Maps
title_full	Learning Intuitive Physics and One-Shot Imitation Using State-Action-Prediction Self-Organizing Maps
title_fullStr	Learning Intuitive Physics and One-Shot Imitation Using State-Action-Prediction Self-Organizing Maps
title_full_unstemmed	Learning Intuitive Physics and One-Shot Imitation Using State-Action-Prediction Self-Organizing Maps
title_sort	learning intuitive physics and one-shot imitation using state-action-prediction self-organizing maps
publisher	Hindawi Limited
publishDate	2021
url	https://doaj.org/article/26375a49689c4365acbf01ed5850008d
work_keys_str_mv	AT martinstetter learningintuitivephysicsandoneshotimitationusingstateactionpredictionselforganizingmaps AT elmarwlang learningintuitivephysicsandoneshotimitationusingstateactionpredictionselforganizingmaps
_version_	1718418387813531648

Learning Intuitive Physics and One-Shot Imitation Using State-Action-Prediction Self-Organizing Maps

Ejemplares similares