High-level representations through unconstrained sensorimotor learning

Name: High-level representations through unconstrained sensorimotor learning
Author: Öztürkçü, Özgür Baran, Uğur, E., Öztop, E.

İsim	High-level representations through unconstrained sensorimotor learning
Yazar	Öztürkçü, Özgür Baran, Uğur, E., Öztop, E.
Basım Tarihi:	2020-10-26
Basım Yeri	- IEEE
Konu	Reinforcement learning symbol generation, Symbol emerge, Symbol grounding
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	978-172817306-1
Kayıt Numarası	6e394ae7-11ae-49f9-bf5f-c57f2015eff0
Tarih	2020-10-26
Örnek Metin	How the sensorimotor experience of an agent can be organized into abstract symbol-like structures to enable effective planning and control is an open question. In the literature, there are many studies that start by assuming the existence of some symbols and 'ground' those onto continuous sensorimotor signals. There are also works that aim to facilitate the emergence of symbol-like representations by using specially designed machine learning architectures. In this paper, we investigate whether a deep reinforcement learning system that learns a dynamic task would facilitate the formation of high-level neural representations that might be considered as precursors of symbolic representation, which could be exploited by higher level neural circuits for better control and planning. The results indicate that without even explicit design to promote such representations, neural responses emerge that may serve as the basis of abstract symbol-like representations.
DOI	10.1109/ICDL-EpiRob48136.2020.9278100

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

High-level representations through unconstrained sensorimotor learning

Yazar Öztürkçü, Özgür Baran, Uğur, E., Öztop, E.

Basım Tarihi 2020-10-26

Basım Yeri - IEEE

Konu Reinforcement learning symbol generation, Symbol emerge, Symbol grounding

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 978-172817306-1

Kayıt Numarası 6e394ae7-11ae-49f9-bf5f-c57f2015eff0

Tarih 2020-10-26

Örnek Metin How the sensorimotor experience of an agent can be organized into abstract symbol-like structures to enable effective planning and control is an open question. In the literature, there are many studies that start by assuming the existence of some symbols and 'ground' those onto continuous sensorimotor signals. There are also works that aim to facilitate the emergence of symbol-like representations by using specially designed machine learning architectures. In this paper, we investigate whether a deep reinforcement learning system that learns a dynamic task would facilitate the formation of high-level neural representations that might be considered as precursors of symbolic representation, which could be exploited by higher level neural circuits for better control and planning. The results indicate that without even explicit design to promote such representations, neural responses emerge that may serve as the basis of abstract symbol-like representations.

DOI 10.1109/ICDL-EpiRob48136.2020.9278100