Comparing Reinforcement Learning and Human Learning using the Game of Hidden Rules

Abstract

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.

arXiv comment9 pages, 4 figures, additional content in appendix

References in corpus (12)

• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
• The Arcade Learning Environment: An Evaluation Platform for General Agents
• Dota 2 with Large Scale Deep Reinforcement Learning
• Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
• StarCraft II: A New Challenge for Reinforcement Learning
• Benchmarking Model-Based Reinforcement Learning
• Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control
• Large-Scale Traffic Signal Control Using a Novel Multi-Agent Reinforcement Learning
• What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study
• The Game of Hidden Rules: A New Kind of Benchmark Challenge for Machine Learning