Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges

•State of the art on continual / lifelong learning and its implications for robotics.•Proposal of a framework to present Continual Learning algorithms.•Summary of existing metrics for continual learning.•Presenting robotics applications for continual learning, current challenges and opportunities. C...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Information fusion Ročník 58; s. 52 - 68
Hlavní autori:	Lesort, Timothée, Lomonaco, Vincenzo, Stoian, Andrei, Maltoni, Davide, Filliat, David, Díaz-Rodríguez, Natalia
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier B.V 01.06.2020 Elsevier
Predmet:	Artificial Intelligence Catastrophic Forgetting Computational Engineering, Finance, and Science Computer Science Computer Vision and Pattern Recognition Continual Learning Deep Learning Lifelong Learning Reinforcement Learning Robotics Reinforcement Learning Continual Learning Catastrophic Forgetting Lifelong Learning Robotics Deep Learning ContinualLearning
ISSN:	1566-2535, 1872-6305
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Buďte prvý, kto okomentuje tento záznam!