Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions
Not on the map. Why?
Abstract (arXiv)
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 HA2: Hierarchical Ad Hoc Agents, a framework leveraging hierarchical reinforcement learning to mimic the structured approach humans use in collaboration. We evaluate HA2 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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 22 of its 44 references that are in the map. First posted on arXiv 7 May 2025.
Builds on
22 of 44 references.
References · 22
- 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
- 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
- 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 345
- 2017FeUdal Networks for Hierarchical Reinforcement Learningcited by 328
- 2020"Other-Play" for Zero-Shot Coordinationcited by 194
- 2020Open Problems in Cooperative AIcited by 167
- 2021Collaborating with Humans without Human Datacited by 139
- 2020RODE: Learning Roles to Decompose Multi-Agent Taskscited by 125
- 2021Off-Belief Learningcited by 72
- 2021Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordinationcited by 69
- 2022A Survey of Ad Hoc Teamwork Researchcited by 41
- 2019Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learningcited by 32
10 more
- 2022K-level Reasoning for Zero-Shot Coordination in Hanabicited by 30
- 2020Too many cooks: Bayesian inference for coordinating multi-agent collaborationcited by 29
- 2023PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordinationcited by 25
- 2024Learning to Cooperate with Humans using Generative Agentscited by 23
- 2022Any-Play: An Intrinsic Augmentation for Zero-Shot Coordinationcited by 22
- 2021Quantifying the effects of environment and population diversity in multi-agent reinforcement learningcited by 21
- 2023Diverse Conventions for Human-AI Collaborationcited by 14
- 2023A Hierarchical Approach to Population Training for Human-AI Collaborationcited by 7
- 2017How to be Helpful? Supportive Behaviors and Personalization for Human-Robot Collaborationcited by 3
- 2021Resonating Minds -- Emergent Collaboration Through Hierarchical Active Inferencecited by 2
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.