Exploration with intrinsic motivation using object–action–outcome latent space

Name: Exploration with intrinsic motivation using object–action–outcome latent space
Author: Sener, M. İ., Nagai, Y., Öztop, Erhan, Uğur, E.

İsim	Exploration with intrinsic motivation using object–action–outcome latent space
Yazar	Sener, M. İ., Nagai, Y., Öztop, Erhan, Uğur, E.
Basım Tarihi:	2023-06
Basım Yeri	- IEEE
Konu	Developmental robotics, Effect prediction, Intrinsic motivation (IM), Open-ended learning, Representation learning
Tür	Süreli Yayın
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	2379-8920
Kayıt Numarası	18b3ac6d-61cb-41c5-904f-ba8c0aa5c755
Lokasyon	Computer Science
Tarih	2023-06
Örnek Metin	One effective approach for equipping artificial agents with sensorimotor skills is to use self-exploration. To do this efficiently is critical, as time and data collection are costly. In this study, we propose an exploration mechanism that blends action, object, and action outcome representations into a latent space, where local regions are formed to host forward model learning. The agent uses intrinsic motivation to select the forward model with the highest learning progress to adopt at a given exploration step. This parallels how infants learn, as high learning progress indicates that the learning problem is neither too easy nor too difficult in the selected region. The proposed approach is validated with a simulated robot in a table-top environment. The simulation scene comprises a robot and various objects, where the robot interacts with one of them each time using a set of parameterized actions and learns the outcomes of these interactions. With the proposed approach, the robot organizes its curriculum of learning as in existing intrinsic motivation approaches and outperforms them in learning speed. Moreover, the learning regime demonstrates features that partially match infant development; in particular, the proposed system learns to predict the outcomes of different skills in a staged manner.
DOI	10.1109/TCDS.2021.3062728
Cilt	15

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Exploration with intrinsic motivation using object–action–outcome latent space

Yazar Sener, M. İ., Nagai, Y., Öztop, Erhan, Uğur, E.

Basım Tarihi 2023-06

Basım Yeri - IEEE

Konu Developmental robotics, Effect prediction, Intrinsic motivation (IM), Open-ended learning, Representation learning

Tür Süreli Yayın

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 2379-8920

Kayıt Numarası 18b3ac6d-61cb-41c5-904f-ba8c0aa5c755

Lokasyon Computer Science

Tarih 2023-06

Örnek Metin One effective approach for equipping artificial agents with sensorimotor skills is to use self-exploration. To do this efficiently is critical, as time and data collection are costly. In this study, we propose an exploration mechanism that blends action, object, and action outcome representations into a latent space, where local regions are formed to host forward model learning. The agent uses intrinsic motivation to select the forward model with the highest learning progress to adopt at a given exploration step. This parallels how infants learn, as high learning progress indicates that the learning problem is neither too easy nor too difficult in the selected region. The proposed approach is validated with a simulated robot in a table-top environment. The simulation scene comprises a robot and various objects, where the robot interacts with one of them each time using a set of parameterized actions and learns the outcomes of these interactions. With the proposed approach, the robot organizes its curriculum of learning as in existing intrinsic motivation approaches and outperforms them in learning speed. Moreover, the learning regime demonstrates features that partially match infant development; in particular, the proposed system learns to predict the outcomes of different skills in a staged manner.

DOI 10.1109/TCDS.2021.3062728

Cilt 15