Date
Publisher
arXiv
Learning often involves interaction between multiple agents. Human teacher-student settings best illustrate how interactions result in efficient knowledge passing where the teacher constructs a curriculum based on their students' abilities. Prior work in machine teaching studies how the teacher should construct optimal teaching datasets assuming the teacher knows everything about the student. However, in the real world, the teacher doesn't have complete information about the student. The teacher must interact and diagnose the student, before teaching. Our work proposes a simple diagnosis algorithm which uses Gaussian processes for inferring student-related information, before constructing a teaching dataset. We apply this to two settings. One is where the student learns from scratch and the teacher must figure out the student's learning algorithm parameters, eg. the regularization parameters in ridge regression or support vector machines. Two is where the student has partially explored the environment and the teacher must figure out the important areas the student has not explored; we study this in the offline reinforcement learning setting where the teacher must provide demonstrations to the student and avoid sending redundant trajectories. Our experiments highlight the importance of diagosing before teaching and demonstrate how students can learn more efficiently with the help of an interactive teacher. We conclude by outlining where diagnosing combined with teaching would be more desirable than passive learning.
Study at a glance
- Question: How can an automated teacher diagnose a learner's needs before choosing what to teach?
- Setting and data: Not stated in the abstract
- Method: Computational experiments testing a diagnosis algorithm (Gaussian processes)
Why it matters
Prior machine teaching assumes teachers know everything about their students. In the real world, teachers do not have complete information and must interact and diagnose students before teaching.
Key findings
- In computational learning models, students learned more efficiently when an interactive teacher diagnosed their abilities before presenting instructional data.
- Diagnosing a learner's prior exploration enables an instructional system to provide targeted demonstrations while avoiding redundant, repetitive material.
- Combining student diagnosis with interactive teaching is more desirable than relying on passive learning.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Why use AI?
Study design
