Title

Machines that Learn and Teach Seamlessly

Authors

Authors

G. Stein; A. J. Gonzalez;C. Barham

Comments

Authors: contact us about adding a copy of your work at STARS@ucf.edu

Abbreviated Journal Title

IEEE Trans. Learn. Technol.

Keywords

Machine learning; intelligent tutoring systems; haptic feedback; teaching agents; learning agents; augmented feedback; psychomotor skill; learning; MINIMALLY INVASIVE SURGERY; HAPTIC FEEDBACK; INSTRUCTION; SIMULATION; TRIAL; Computer Science, Interdisciplinary Applications; Education &; Educational Research

Abstract

This paper describes an investigation into creating agents that can learn how to perform a task by observing an expert, then seamlessly turn around and teach the same task to a less proficient person. These agents are taught through observation of expert performance and thereafter refined through unsupervised practice of the task, all on a simulated environment. A less proficient human is subsequently taught by the now-trained agent through a third approach-coaching, executed through a haptic device. This approach addresses tasks that involve complex psychomotor skills. A machine-learning algorithm called PIGEON is used to teach the agents. A prototype is built and then tested on a task involving the manipulation of a crane to move large container boxes in a simulated shipyard. Two evaluations were performed-a proficiency test and a learning rate test. These tests were designed to determine whether this approach improves the human learning more than self-experimentation by the human. While the test results do not conclusively show that our approach provides improvement over self-learning, some positive aspects of the results suggest great potential for this approach.

Journal Title

Ieee Transactions on Learning Technologies

Volume

6

Issue/Number

4

Publication Date

1-1-2013

Document Type

Article

Language

English

First Page

389

Last Page

402

WOS Identifier

WOS:000328694400009

ISSN

1939-1382

Share

COinS