Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Capturing Skill State in Curriculum Learning for Human Skill Acquisition

Capturing Skill State in Curriculum Learning for Human Skill Acquisition.
Keya Ghonasgi, Reuth Mirsky, Sanmit Narvekar, Bharath Masetty, Adrian M. Haith, Peter Stone, and Ashish D. Deshpande.
In International Conference on Intelligent Robots and Systems (IROS), September 2021.
Video presentation

Download

[PDF]1.6MB  

Abstract

Humans learn complex motor skills with practice and training. Though the learning process is not fully understood, several theories from motor learning, neuroscience, education, and game design suggest that curriculum-based training may be the key to efficient skill acquisition. However, designing such a curriculum and understanding its effects on learning are challenging problems. In this paper, we define the Human-skill Curriculum Markov Decision Process (H-CMDP) to systematize the design of training protocols. We also identify a vocabulary of performance features to enable the approximation for a human's skill level across a variety of cognitive and motor tasks. A novel task domain is introduced as a testbed to evaluate the effectiveness of our approach. Human subject experiments show that (1) participants can learn to improve their performance in tasks within this domain, (2) the learning is quantifiable via our performance features, and (3) the domain is flexible enough to create distinct levels of difficulty. The long-term goal of this work is to systematize the process of curriculum-based training toward the design of protocols for robot-mediated rehabilitation.

BibTeX Entry

@InProceedings{IROS2021-REUTH,
  author = {Keya Ghonasgi and Reuth Mirsky and Sanmit Narvekar and Bharath Masetty and Adrian M. Haith and Peter Stone and Ashish D. Deshpande},
  title = {Capturing Skill State in Curriculum Learning for Human Skill Acquisition},
  booktitle = {International Conference on Intelligent Robots and Systems (IROS)},
  location = {Virtual},
  month = {September},
  year = {2021},
  abstract = {
        Humans learn complex motor skills with practice and
        training. Though the learning process is not fully understood,
        several theories from motor learning, neuroscience, education,
        and game design suggest that curriculum-based training may be
        the key to efficient skill acquisition.  However, designing
        such a curriculum and understanding its effects on learning
        are challenging problems. In this paper, we define the
        Human-skill Curriculum Markov Decision Process (H-CMDP) to
        systematize the design of training protocols. We also identify
        a vocabulary of performance features to enable the
        approximation for a human's skill level across a variety of
        cognitive and motor tasks. A novel task domain is introduced
        as a testbed to evaluate the effectiveness of our
        approach. Human subject experiments show that (1) participants
        can learn to improve their performance in tasks within this
        domain, (2) the learning is quantifiable via our performance
        features, and (3) the domain is flexible enough to create
        distinct levels of difficulty. The long-term goal of this work
        is to systematize the process of curriculum-based training
        toward the design of protocols for robot-mediated
        rehabilitation.
  },
  wwwnote = {<a href="https://youtu.be/TI1Zh4L63Xw">Video presentation</a>}
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed Nov 17, 2021 22:18:59