Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions

Stéphane Aroca-Ouellette, Miguel Aroca-Ouellette, Katharina von der Wense, Alessandro Roncone

Keywords: Human-Agent Interaction, Ad Hoc Teaming, Zero-Shot Coordination, Hierarchical Reinforcement Learning

TL;DR: We demonstrate that agents with human interpretable (i.e. shared) task abstractions improve human-agent teaming.

Abstract: In collaborative tasks, autonomous agents fall short of humans in their capability to quickly adapt to new and unfamiliar teammates. We posit that a limiting factor for zero-shot coordination is the lack of shared task abstractions, a mechanism humans rely on to implicitly align with teammates. To address this gap, we introduce HA$^2$: Hierarchical Ad Hoc Agents, a framework leveraging hierarchical reinforcement learning to mimic the structured approach humans use in collaboration. We evaluate HA$^2$ in the Overcooked environment, demonstrating statistically significant improvement over baselines when paired with both unseen agents and humans, providing better resilience to environmental shifts, and outperforming state-of-the-art methods.

Paper Type: Previously Published Paper

Venue For Previously Published Paper: IJCAI 2025

Submission Number: 10