Comparing Reinforcement Learning and Human Learning using the Game of Hidden Rules
This work addresses the need for a task-oriented understanding to improve the design of human-machine systems, though it is incremental as it focuses on creating a tool for study rather than advancing learning methods directly.
The authors tackled the challenge of comparing reinforcement learning (RL) and human learning (HL) by developing a learning environment designed to study the impact of task structure on performance, demonstrating its utility through experiments that reveal performance differences between humans and RL algorithms.
Reliable real-world deployment of reinforcement learning (RL) methods requires a nuanced understanding of their strengths and weaknesses and how they compare to those of humans. Human-machine systems are becoming more prevalent and the design of these systems relies on a task-oriented understanding of both human learning (HL) and RL. Thus, an important line of research is characterizing how the structure of a learning task affects learning performance. While increasingly complex benchmark environments have led to improved RL capabilities, such environments are difficult to use for the dedicated study of task structure. To address this challenge we present a learning environment built to support rigorous study of the impact of task structure on HL and RL. We demonstrate the environment's utility for such study through example experiments in task structure that show performance differences between humans and RL algorithms.