Facial Feedback for Reinforcement Learning: A Case Study and Offline Analysis Using the TAMER Framework

TL;DR

This study explores using facial expressions as evaluative feedback in reinforcement learning, demonstrating that it can improve agent training efficiency and effectiveness through a large-scale human study and predictive modeling.

Contribution

It introduces a novel approach of interpreting facial expressions as feedback in TAMER, and shows that this method enhances learning performance in a benchmark environment.

Findings

Facial expressions can be effectively used as evaluative feedback.

Predictive models of facial feedback improve agent performance.

Bi-directional feedback and competition enhance training outcomes.

Abstract

Interactive reinforcement learning provides a way for agents to learn to solve tasks from evaluative feedback provided by a human user. Previous research showed that humans give copious feedback early in training but very sparsely thereafter. In this article, we investigate the potential of agent learning from trainers' facial expressions via interpreting them as evaluative feedback. To do so, we implemented TAMER which is a popular interactive reinforcement learning method in a reinforcement-learning benchmark problem --- Infinite Mario, and conducted the first large-scale study of TAMER involving 561 participants. With designed CNN-RNN model, our analysis shows that telling trainers to use facial expressions and competition can improve the accuracies for estimating positive and negative feedback using facial expressions. In addition, our results with a simulation experiment show that learning solely from predicted feedback based on facial expressions is possible and using strong/effective prediction models or a regression method, facial responses would significantly improve the performance of agents. Furthermore, our experiment supports previous studies demonstrating the importance of bi-directional feedback and competitive elements in the training interface.