%0 Conference Proceedings
%T Interactive Learning from Unlabeled Instructions
%+ École Nationale Supérieure de Techniques Avancées (ENSTA Paris)
%+ Flowing Epigenetic Robots and Systems (Flowers)
%+ Departamento de Informática e Ingeniería de Sistemas (DIIS)
%A Grizou, Jonathan
%A Iturrate, Iñaki
%A Montesano, Luis
%A Oudeyer, Pierre-Yves
%A Lopes, Manuel
%Z ERC EXPLORER 24007
%< avec comité de lecture
%B UAI-30th Conference on Uncertainty in Artificial Intelligence
%C Quebec, Canada
%P 1-8
%8 2014-07-23
%D 2014
%K Interactive Learning
%K Adaptive interfaces
%K User Modeling
%K Planning under Uncertainty
%K Sequential Decision Making
%K Brain-Computer Interaction
%Z Computer Science [cs]/Machine Learning [cs.LG]
%Z Computer Science [cs]/Robotics [cs.RO]Conference papers
%X Interactive learning deals with the problem of learning and solving tasks using human instructions. It is common in human-robot interaction, tutoring systems, and in human-computer interfaces such as brain-computer ones. In most cases, learning these tasks is possible because the signals are predefined or an ad-hoc calibration procedure allows to map signals to specific meanings. In this paper, we address the problem of simultaneously solving a task under human feedback and learning the associated meanings of the feedback signals. This has important practical application since the user can start controlling a device from scratch, without the need of an expert to define the meaning of signals or carrying out a calibration phase. The paper proposes an algorithm that simultaneously assign meanings to signals while solving a sequential task under the assumption that both, human and machine, share the same a priori on the possible instruction meanings and the possible tasks. Furthermore, we show using synthetic and real EEG data from a brain-computer interface that taking into account the uncertainty of the task and the signal is necessary for the machine to actively plan how to solve the task efficiently.
%G English
%2 https://hal.science/hal-01007689/document
%2 https://hal.science/hal-01007689/file/grizou2014interactive.pdf
%L hal-01007689
%U https://hal.science/hal-01007689
%~ ENSTA
%~ INRIA
%~ INRIA-BORDEAUX
%~ PARISTECH
%~ INRIA_TEST
%~ TESTALAIN1
%~ TESTBORDEAUX
%~ INRIA2