Human-AI Collaboration in Real-World Complex Environment with Reinforcement Learning

TL;DR

This paper demonstrates that human-AI collaboration in complex environments, facilitated by reinforcement learning, enhances performance, reduces human effort, and accelerates learning compared to autonomous AI or human-only control.

Contribution

It introduces a new simulation environment for critical infrastructure protection and shows that human-AI teaming outperforms human-only or AI-only approaches in complex tasks.

Findings

Human-AI collaboration outperforms human-only and AI-only agents.

Learning from human policy correction accelerates agent learning.

Collaboration reduces human mental and temporal demands.

Abstract

Recent advances in reinforcement learning (RL) and Human-in-the-Loop (HitL) learning have made human-AI collaboration easier for humans to team with AI agents. Leveraging human expertise and experience with AI in intelligent systems can be efficient and beneficial. Still, it is unclear to what extent human-AI collaboration will be successful, and how such teaming performs compared to humans or AI agents only. In this work, we show that learning from humans is effective and that human-AI collaboration outperforms human-controlled and fully autonomous AI agents in a complex simulation environment. In addition, we have developed a new simulator for critical infrastructure protection, focusing on a scenario where AI-powered drones and human teams collaborate to defend an airport against enemy drone attacks. We develop a user interface to allow humans to assist AI agents effectively. We demonstrated that agents learn faster while learning from policy correction compared to learning from humans or agents. Furthermore, human-AI collaboration requires lower mental and temporal demands, reduces human effort, and yields higher performance than if humans directly controlled all agents. In conclusion, we show that humans can provide helpful advice to the RL agents, allowing them to improve learning in a multi-agent setting.