Implicitly Aligning Humans And Autonomous Agents Through Shared Task Abstractions

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 existing baselines when paired with both unseen agents and humans, providing better resilience to environmental shifts, and outperforming all state-of-the-art methods.

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keyarocaouellette2025implicitly

Related papers

• Human-ai Coordination Via Human-regularized Search And Learning (2022)0.00
• Tackling Cooperative Incompatibility For Zero-shot Human-ai Coordination (2023)0.00
• Reinforcement Learning On Human Decision Models For Uniquely Collaborative AI Teammates (2021)0.00
• Collaborating With Humans Without Human Data (2021)0.00
• Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In The Game Of Hanabi (2023)0.00
• Zero-shot Coordination In Ad Hoc Teams With Generalized Policy Improvement And Difference Rewards (2025)0.00
• Adaptive Agent Architecture For Real-time Human-agent Teaming (2021)0.00
• A Hierarchical Approach To Population Training For Human-ai Collaboration (2023)0.00