Teaching to Learn: Sequential Teaching of Agents with Inner States

09/14/2020
by   Mustafa Mert Çelikok, et al.
10

In sequential machine teaching, a teacher's objective is to provide the optimal sequence of inputs to sequential learners in order to guide them towards the best model. In this paper we extend this setting from current static one-data-set analyses to learners which change their learning algorithm or latent state to improve during learning, and to generalize to new datasets. We introduce a multi-agent formulation in which learners' inner state may change with the teaching interaction, which affects the learning performance in future tasks. In order to teach such learners, we propose an optimal control approach that takes the future performance of the learner after teaching into account. This provides tools for modelling learners having inner states, and machine teaching of meta-learning algorithms. Furthermore, we distinguish manipulative teaching, which can be done by effectively hiding data and also used for indoctrination, from more general education which aims to help the learner become better at generalization and learning in new datasets in the absence of a teacher.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/30/2017

Iterative Machine Teaching

In this paper, we consider the problem of machine teaching, the inverse ...
research
10/15/2018

An Optimal Control Approach to Sequential Machine Teaching

Given a sequential learning algorithm and a target model, sequential mac...
research
11/29/2019

Class Teaching for Inverse Reinforcement Learners

In this paper we propose the first machine teaching algorithm for multip...
research
10/16/2012

Dynamic Teaching in Sequential Decision Making Environments

We describe theoretical bounds and a practical algorithm for teaching a ...
research
12/22/2020

Teaching young learners a foreign language via tangible and graphical user interfaces

The use of tangible interfaces in teaching has been proved more effectiv...
research
09/05/2020

Using Machine Teaching to Investigate Human Assumptions when Teaching Reinforcement Learners

Successful teaching requires an assumption of how the learner learns - h...
research
04/17/2018

Unlearn What You Have Learned: Adaptive Crowd Teaching with Exponentially Decayed Memory Learners

With the increasing demand for large amount of labeled data, crowdsourci...

Please sign up or login with your details

Forgot password? Click here to reset