Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions
This addresses the challenge of zero-shot coordination in human-agent collaboration, offering a domain-specific solution for improving adaptability in multi-agent systems.
The paper tackles the problem of autonomous agents' inability to adapt quickly to new teammates in collaborative tasks by introducing HA^2, a hierarchical reinforcement learning framework that mimics human shared task abstractions, achieving statistically significant improvements over state-of-the-art methods in the Overcooked environment.
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 existing baselines when paired with both unseen agents and humans, providing better resilience to environmental shifts, and outperforming all state-of-the-art methods.