Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910931570655232 |
|---|---|
| author | Aroca-Ouellette, Stéphane Aroca-Ouellette, Miguel von der Wense, Katharina Roncone, Alessandro |
| author_facet | Aroca-Ouellette, Stéphane Aroca-Ouellette, Miguel von der Wense, Katharina Roncone, Alessandro |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04579 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions Aroca-Ouellette, Stéphane Aroca-Ouellette, Miguel von der Wense, Katharina Roncone, Alessandro Multiagent Systems Machine Learning 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. |
| title | Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions |
| topic | Multiagent Systems Machine Learning |
| url | https://arxiv.org/abs/2505.04579 |