Human Engagement Providing Evaluative and Informative Advice for Interactive Reinforcement Learning

TL;DR

This study compares evaluative and informative human advice in interactive reinforcement learning, finding that informative advice leads to higher accuracy, greater engagement, and longer assistance from humans.

Contribution

It introduces an experimental setup to compare human engagement with evaluative versus informative advice in reinforcement learning.

Findings

Informative advice results in more accurate guidance.

Humans provide more advice and stay engaged longer with informative methods.

Participants perceive agents following informative advice as more accurate.

Abstract

Interactive reinforcement learning proposes the use of externally-sourced information in order to speed up the learning process. When interacting with a learner agent, humans may provide either evaluative or informative advice. Prior research has focused on the effect of human-sourced advice by including real-time feedback on the interactive reinforcement learning process, specifically aiming to improve the learning speed of the agent, while minimising the time demands on the human. This work focuses on answering which of two approaches, evaluative or informative, is the preferred instructional approach for humans. Moreover, this work presents an experimental setup for a human-trial designed to compare the methods people use to deliver advice in terms of human engagement. The results obtained show that users giving informative advice to the learner agents provide more accurate advice, are willing to assist the learner agent for a longer time, and provide more advice per episode. Additionally, self-evaluation from participants using the informative approach has indicated that the agent's ability to follow the advice is higher, and therefore, they feel their own advice to be of higher accuracy when compared to people providing evaluative advice.