Leveraging human knowledge in tabular reinforcement learning: A study of human subjects

TL;DR

This study empirically evaluates various methods of injecting human knowledge into reinforcement learning, highlighting the effectiveness of reward shaping and introducing SASS as a complementary technique that reduces human effort.

Contribution

The paper presents the first empirical comparison of human knowledge injection methods in RL, including a novel SASS method based on state-action similarities.

Findings

Reward shaping is the most natural and effective method for speeding up RL.

SASS can be combined with reward shaping to enhance efficiency.

The proposed SASS method requires minimal additional effort from human designers.

Abstract

Reinforcement Learning (RL) can be extremely effective in solving complex, real-world problems. However, injecting human knowledge into an RL agent may require extensive effort and expertise on the human designer's part. To date, human factors are generally not considered in the development and evaluation of possible RL approaches. In this article, we set out to investigate how different methods for injecting human knowledge are applied, in practice, by human designers of varying levels of knowledge and skill. We perform the first empirical evaluation of several methods, including a newly proposed method named SASS which is based on the notion of similarities in the agent's state-action space. Through this human study, consisting of 51 human participants, we shed new light on the human factors that play a key role in RL. We find that the classical reward shaping technique seems to be the most natural method for most designers, both expert and non-expert, to speed up RL. However, we further find that our proposed method SASS can be effectively and efficiently combined with reward shaping, and provides a beneficial alternative to using only a single speedup method with minimal human designer effort overhead.