Putting Humans in Humans and AI: How to Incorporate Real People in Human-Agent Interaction

As more and more multi-agent systems are deployed in the real world, it becomes imperative to study these systems with real humans to avoid unexpected negative consequences during deployment. Yet, this can be challenging for researchers with more experience designing algorithms and less experience running human participant experiments. In this tutorial, we will discuss the state of the human-agent interaction field, emphasizing (i) incorporating humans into multi-agent systems, including reinforcement learning systems, (ii) investigating when to rely on human vs. AI strengths, and (iii) designing human-AI studies to evaluate algorithms with real humans.