Intrinsically Motivated Open-Ended Multi-Task Learning Using Transfer Learning to Discover Task Hierarchy - IMT Atlantique Accéder directement au contenu
Article Dans Une Revue Applied Sciences Année : 2021

Intrinsically Motivated Open-Ended Multi-Task Learning Using Transfer Learning to Discover Task Hierarchy

Résumé

In open-ended continuous environments, robots need to learn multiple parameterised control tasks in hierarchical reinforcement learning. We hypothesise that the most complex tasks can be learned more easily by transferring knowledge from simpler tasks, and faster by adapting the complexity of the actions to the task. We propose a task-oriented representation of complex actions, called procedures, to learn online task relationships and unbounded sequences of action primitives to control the different observables of the environment. Combining both goal-babbling with imitation learning, and active learning with transfer of knowledge based on intrinsic motivation, our algorithm self-organises its learning process. It chooses at any given time a task to focus on; and what, how, when and from whom to transfer knowledge. We show with a simulation and a real industrial robot arm, in cross-task and cross-learner transfer settings, that task composition is key to tackle highly complex tasks. Task decomposition is also efficiently transferred across different embodied learners and by active imitation, where the robot requests just a small amount of demonstrations and the adequate type of information. The robot learns and exploits task dependencies so as to learn tasks of every complexity.
Fichier principal
Vignette du fichier
Duminy20021AS.pdf (2.36 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03118190 , version 1 (18-02-2021)

Identifiants

Citer

Nicolas Duminy, Sao Mai Nguyen, Junshuai Zhu, Dominique Duhaut, Jerome Kerdreux. Intrinsically Motivated Open-Ended Multi-Task Learning Using Transfer Learning to Discover Task Hierarchy. Applied Sciences, 2021, 11 (3), pp.975. ⟨10.3390/app11030975⟩. ⟨hal-03118190⟩
313 Consultations
175 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More