A model for cognitively valid lifelong learning

Name: A model for cognitively valid lifelong learning
Author: Say, H., Öztop, Erhan

İsim	A model for cognitively valid lifelong learning
Yazar	Say, H., Öztop, Erhan
Basım Tarihi:	2023
Basım Yeri	- IEEE
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	979-835032570-6
Kayıt Numarası	fbd715be-9140-493c-8c00-489e24a21cb1
Lokasyon	Computer Science
Tarih	2023
Notlar	New Energy and Industrial Technology Development Organization ; Japan Science and Technology Agency ; Core Research for Evolutional Science and Technology
Örnek Metin	In continual learning, usually a sequence of tasks are given to a learning agent and the performance of the agent after learning is measured in terms of resistance to catastrophic forgetting, efficacy of knowledge transfer and overall performance on the individual tasks. On the other hand, in multi-task learning, the system is designed to simultaneously acquire knowledge in multiple tasks, often through offline batch learning. A more cognitively valid scenario for lifelong robot learning would be to have a robotic agent to autonomously decide which task to engage and disengage while leveraging many-to-many knowledge transfer ability among tasks during online learning. In this study, we propose a novel lifelong robot learning architecture to fulfill the aforementioned desiderata, and show its validity in an environment where a robot learns the effects of its actions in different task settings. To realize the proposed model, we adopt learning progress measure for task selection, and have the tasks learn by independent neural networks with special structure that allows access to the neural layers of the non-selected tasks. The experiments conducted with a simulated robot arm in an object interaction scenario show that the proposed architecture yields better knowledge transfer and facilitates faster learning compared to baselines of fixed sequence task learning and isolated task learners with no knowledge transfer.
DOI	10.1109/ROBIO58561.2023.10355028

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

A model for cognitively valid lifelong learning

Yazar Say, H., Öztop, Erhan

Basım Tarihi 2023

Basım Yeri - IEEE

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 979-835032570-6

Kayıt Numarası fbd715be-9140-493c-8c00-489e24a21cb1

Lokasyon Computer Science

Tarih 2023

Notlar New Energy and Industrial Technology Development Organization ; Japan Science and Technology Agency ; Core Research for Evolutional Science and Technology

Örnek Metin In continual learning, usually a sequence of tasks are given to a learning agent and the performance of the agent after learning is measured in terms of resistance to catastrophic forgetting, efficacy of knowledge transfer and overall performance on the individual tasks. On the other hand, in multi-task learning, the system is designed to simultaneously acquire knowledge in multiple tasks, often through offline batch learning. A more cognitively valid scenario for lifelong robot learning would be to have a robotic agent to autonomously decide which task to engage and disengage while leveraging many-to-many knowledge transfer ability among tasks during online learning. In this study, we propose a novel lifelong robot learning architecture to fulfill the aforementioned desiderata, and show its validity in an environment where a robot learns the effects of its actions in different task settings. To realize the proposed model, we adopt learning progress measure for task selection, and have the tasks learn by independent neural networks with special structure that allows access to the neural layers of the non-selected tasks. The experiments conducted with a simulated robot arm in an object interaction scenario show that the proposed architecture yields better knowledge transfer and facilitates faster learning compared to baselines of fixed sequence task learning and isolated task learners with no knowledge transfer.

DOI 10.1109/ROBIO58561.2023.10355028