Interaction for Task Instruction and Learning
A. L. Thomaz et al., “Interaction for Task Instruction and Learning,” in Interactive Task Learning: Agents, Robots, and Humans Acquiring New Tasks through Natural Interactions, K. A. Gluck and J. E. Laird, Eds. MIT Press, 2019.
Abstract
This chapter considers the qualities of human interaction and learning that will be most effective and natural to incorporate into any interactive task learning agent, and focuses specifically on the interactions involved in learning from explicit instruction. At the center of this interaction is a process that brings the common ground between a teacher agent and a learner agent into alignment. Errors or misalignments to this common ground drive the interactive learning process. The importance of timing is high- lighted as is the dynamics of an interaction, as a communication channel itself, in this alignment process.
BibTeX Entry
@incollection{thomaz2019esforum,
title = {Interaction for Task Instruction and Learning},
author = {Thomaz, Andrea L. and Lieven, Elena and Cakmak, Maya and Chai, Joyce Y. and Garrod, Simon and Gray, Wayne D. and Levinson, Stephen C. and Paiva, Ana and Russwinkel, Nele},
year = {2019},
type = {chapter},
booktitle = {Interactive Task Learning: Agents, Robots, and Humans Acquiring New Tasks through Natural Interactions},
editor = {Gluck, K. A. and Laird, J. E.},
publisher = {MIT Press},
chapter = {7},
doi = {10.7551/mitpress/11956.003.0011}
}