Eliciting good teaching from humans for machine learners

Abstract

Interactive machine learningWe propose using computational teaching algorithms to improve human teaching for machine learners. We investigate example sequences produced naturally by human teachers and find that humans often do not spontaneously generate optimal teaching sequences for arbitrary machine learners. To elicit better teaching, we propose giving humans teaching guidance, which are instructions on how to teach, derived from computational teaching algorithms or heuristics. We present experimental results demonstrating that teaching guidance substantially improves human teaching in three different problem domains. This provides promising evidence that human intelligence and flexibility can be leveraged to achieve better sample efficiency when input data to a learning system comes from a human teacher.

Quantifying teaching behavior in robot learning from demonstration

“…The ability to analyse teaching behaviour is critical to improving LfD performance. It can be shown that an optimal teacher can theoretically provide the minimum number of samples required to teach a learner a task, called the teaching dimension (Goldman and Kearns, 1995;Balbach and Zeugmann, 2009;Khan et al, 2011;Cakmak and Thomaz, 2014;Zhu, 2015), by providing non-i.i.d. samples to the learner which exploit the task structure and learning method employed.…”

“…can be attributed to teachers lacking a shared mental model with the robot, or a lack of understanding of how and what the robot learns during the teaching process (Cakmak and Thomaz, 2014;Hellström and Bensch, 2018).…”

Active Robot Learning for Temporal Task Models

“…Although interactive robots can outperform passive ones in both performance and quality of the interaction, a careful design of the Human-Robot interaction (HRI) is needed. Aspects like the transparency of the robot learning process [11,33], the ability of the user to be a good teacher [9], the timing of the queries or the balance in control over the interaction [7] must be taken into account. Furthermore, efficient ways to mediate between the robot's internal skill representation and the user need to be crafted.…”

Teaching Human Teachers to Teach Robot Learners

“…Videos are used for experiment instruction to help ensure consistency in the participants' prior knowledge for each teaching phase, and to remove the risk of the researcher providing more or less information on how to complete the task between participants. Additionally, as noted in [13], video instruction is a highly effective teaching tool for novice users.…”