Continual learning (CL) is a particular machine learning paradigm where the data distribution and learning objective change through time, or where all the training data and objective criteria are never available at once. The evolution of the learning process is modeled by a sequence of learning experiences where the goal is to be able to learn new skills all along the sequence without forgetting what has been previously learned. CL can be seen as an online learning where knowledge fusion needs to take place in order to learn from streams of data presented sequentially in time. Continual learning also aims at the same time at optimizing the memory, the computation power and the speed during the learning process. An important challenge for machine learning is not necessarily finding solutions that work in the real world but rather finding stable algorithms that can learn in real world. Hence, the ideal approach would be tackling the real world in a embodied platform: an autonomous agent. Continual learning would then be effective in an autonomous agent or robot, which would learn autonomously through time about the external world, and incrementally develop a set of complex skills and knowledge.Robotic agents have to learn to adapt and interact with their environment using a continuous stream of observations. Some recent approaches aim at tackling continual learning for robotics, but most recent papers on continual learning only experiment approaches in simulation or with static datasets. Unfortunately, the evaluation of those algorithms does not provide insights on whether their solutions may help continual learning in the context of robotics. This paper aims at reviewing the existing state of the art of continual learning, summarizing existing benchmarks and metrics, and proposing a framework for presenting and evaluating both robotics and non robotics approaches in a way that makes transfer between both fields easier. We put light on continual learning in the context of robotics to create connections between fields and normalize approaches.

Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges / Lesort, Timothée; Lomonaco, Vincenzo; Stoian, Andrei; Maltoni, Davide; Filliat, David; Díaz-Rodríguez, Natalia. - In: INFORMATION FUSION. - ISSN 1566-2535. - ELETTRONICO. - 58:(2020), pp. 52-68. [10.1016/j.inffus.2019.12.004]

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

Lomonaco, Vincenzo;Maltoni, Davide;
2020

Abstract

Continual learning (CL) is a particular machine learning paradigm where the data distribution and learning objective change through time, or where all the training data and objective criteria are never available at once. The evolution of the learning process is modeled by a sequence of learning experiences where the goal is to be able to learn new skills all along the sequence without forgetting what has been previously learned. CL can be seen as an online learning where knowledge fusion needs to take place in order to learn from streams of data presented sequentially in time. Continual learning also aims at the same time at optimizing the memory, the computation power and the speed during the learning process. An important challenge for machine learning is not necessarily finding solutions that work in the real world but rather finding stable algorithms that can learn in real world. Hence, the ideal approach would be tackling the real world in a embodied platform: an autonomous agent. Continual learning would then be effective in an autonomous agent or robot, which would learn autonomously through time about the external world, and incrementally develop a set of complex skills and knowledge.Robotic agents have to learn to adapt and interact with their environment using a continuous stream of observations. Some recent approaches aim at tackling continual learning for robotics, but most recent papers on continual learning only experiment approaches in simulation or with static datasets. Unfortunately, the evaluation of those algorithms does not provide insights on whether their solutions may help continual learning in the context of robotics. This paper aims at reviewing the existing state of the art of continual learning, summarizing existing benchmarks and metrics, and proposing a framework for presenting and evaluating both robotics and non robotics approaches in a way that makes transfer between both fields easier. We put light on continual learning in the context of robotics to create connections between fields and normalize approaches.
2020
Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges / Lesort, Timothée; Lomonaco, Vincenzo; Stoian, Andrei; Maltoni, Davide; Filliat, David; Díaz-Rodríguez, Natalia. - In: INFORMATION FUSION. - ISSN 1566-2535. - ELETTRONICO. - 58:(2020), pp. 52-68. [10.1016/j.inffus.2019.12.004]
Lesort, Timothée; Lomonaco, Vincenzo; Stoian, Andrei; Maltoni, Davide; Filliat, David; Díaz-Rodríguez, Natalia
File in questo prodotto:
File Dimensione Formato  
inffus2020-58.pdf

accesso aperto

Tipo: Postprint
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione - Non commerciale - Non opere derivate (CCBYNCND)
Dimensione 1.65 MB
Formato Adobe PDF
1.65 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/713396
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 194
  • ???jsp.display-item.citation.isi??? 156
social impact