Should artificial agents ask for help in human-robot collaborative problem-solving?

TL;DR

This study investigates whether artificial agents and children benefit similarly from expert help in collaborative problem-solving, using the Towers of Hanoi task to compare reinforcement learning algorithms and human behavior.

Contribution

It demonstrates that a Q-learning algorithm benefits from expert help in the same way children do, validating hypotheses from human-robot interaction studies.

Findings

Q-learning benefits from expert help similarly to children

Help accelerates learning in both artificial agents and humans

Intervention type (canonical or requested) does not significantly affect outcomes

Abstract

Transferring as fast as possible the functioning of our brain to artificial intelligence is an ambitious goal that would help advance the state of the art in AI and robotics. It is in this perspective that we propose to start from hypotheses derived from an empirical study in a human-robot interaction and to verify if they are validated in the same way for children as for a basic reinforcement learning algorithm. Thus, we check whether receiving help from an expert when solving a simple close-ended task (the Towers of Hano\"i) allows to accelerate or not the learning of this task, depending on whether the intervention is canonical or requested by the player. Our experiences have allowed us to conclude that, whether requested or not, a Q-learning algorithm benefits in the same way from expert help as children do.