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.
|Title of host publication||IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||6|
|State||Published - 2021|
|Event||2021 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021 - Prague, Czech Republic|
Duration: 27 Sep 2021 → 1 Oct 2021
|Name||IEEE International Conference on Intelligent Robots and Systems|
|Conference||2021 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021|
|Period||27/09/21 → 1/10/21|
Bibliographical noteFunding Information:
This work has taken place with joint efforts from the ReNeu Robotics Lab and Learning Agents Research Group (LARG) at UT Austin. Effort in the ReNeu Lab is supported, in part, by Facebook Reality Lab and NSF (M3X-2019704). LARG research is supported in part by NSF (CPS-1739964, IIS-1724157, NRI-1925082, CMMI-2019704), ONR (N00014-18-2243), FLI (RFP2-000), ARO (W911NF-19-2-0333), DARPA, Lockheed Martin, GM, and Bosch. Peter Stone serves as the Executive Director of Sony AI America and receives financial compensation for this work. The terms of this arrangement have been reviewed and approved by the University of Texas at Austin in accordance with its policy on objectivity in research.
∗ This paper contains material from a preliminary workshop version . Compared to the workshop version, this manuscript has been extended with additional formalization and experiments. None of the material has appeared in a previous conference paper. This work is supported by NSF (M3X-2019704).
© 2021 IEEE.