Using Machine Teaching to Investigate Human Assumptions when Teaching Reinforcement Learners

TL;DR

This paper explores human assumptions about teaching reinforcement learners, specifically Q-learning agents, through behavioral experiments and machine teaching optimization, revealing insights into effective teaching strategies and human biases.

Contribution

It introduces a normative machine teaching framework for Q-learning and investigates human assumptions, highlighting suboptimal teaching behaviors and the impact of real-time feedback.

Findings

People teach Q-learners efficiently with low discount and high learning rates.

Humans are only partially optimal in their teaching strategies.

Real-time updates of learner states slightly improve teaching effectiveness.

Abstract

Successful teaching requires an assumption of how the learner learns - how the learner uses experiences from the world to update their internal states. We investigate what expectations people have about a learner when they teach them in an online manner using rewards and punishment. We focus on a common reinforcement learning method, Q-learning, and examine what assumptions people have using a behavioral experiment. To do so, we first establish a normative standard, by formulating the problem as a machine teaching optimization problem. To solve the machine teaching optimization problem, we use a deep learning approximation method which simulates learners in the environment and learns to predict how feedback affects the learner's internal states. What do people assume about a learner's learning and discount rates when they teach them an idealized exploration-exploitation task? In a behavioral experiment, we find that people can teach the task to Q-learners in a relatively efficient and effective manner when the learner uses a small value for its discounting rate and a large value for its learning rate. However, they still are suboptimal. We also find that providing people with real-time updates of how possible feedback would affect the Q-learner's internal states weakly helps them teach. Our results reveal how people teach using evaluative feedback and provide guidance for how engineers should design machine agents in a manner that is intuitive for people.