mlsanityData to 14 Oct 2026

Adaptive Human-AI Coordination via Hierarchical Action Disentanglement

arXiv 2605.24343 ↗First posted 23 May 2026cs.AIcited by 0

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

Human-AI collaboration requires agents that can adapt to diverse partner behaviors and skill levels while remaining robust to unseen partners. Existing methods often collapse to a single dominant behavior or learn poorly aligned skills, limiting effective coordination. We propose Intrinsic Action Disentanglement (IAD), a deep hierarchical reinforcement learning (DHRL) framework that learns distinct, partner-aware low-level action sequences conditioned on high-level latent skills. IAD introduces an intrinsic reward that explicitly encourages disentangled action distributions of the agent's low-level policy across skills, yielding an interpretable mapping between high-level decisions and partner-specific behavioral responses. By capturing temporally extended interaction patterns, IAD enables flexible adaptation to heterogeneous partner dynamics under distributional shift. We evaluate IAD in the Overcooked-AI domain across multiple layouts and diverse partner settings, including unseen simulated partners, a human-proxy model trained on human-human gameplay, and real human partners. Results show that IAD consistently outperforms strong baselines and achieves more reliable, adaptive coordination across all settings.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 17 of its 24 references that are in the map. First posted on arXiv 23 May 2026.

Builds on

17 of 24 references.

References · 17

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  3. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 752
  4. 2016The Option-Critic Architecturecited by 448
  5. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 349
  6. 2017FeUdal Networks for Hierarchical Reinforcement Learningcited by 337
  7. 2016Variational Intrinsic Controlcited by 267
  8. 2020"Other-Play" for Zero-Shot Coordinationcited by 198
  9. 2019The Hanabi Challenge: A New Frontier for AI Researchcited by 197
  10. 2021Collaborating with Humans without Human Datacited by 142
  11. 2020Towards Playing Full MOBA Games with Deep Reinforcement Learningcited by 78
  12. 2021Hierarchical Reinforcement Learning By Discovering Intrinsic Optionscited by 58
5 more
  1. 2019Sub-policy Adaptation for Hierarchical Reinforcement Learningcited by 47
  2. 2023Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biasedcited by 37
  3. 2021Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversitycited by 22
  4. 2023A Hierarchical Approach to Population Training for Human-AI Collaborationcited by 7
  5. 2024BCR-DRL: Behavior- and Context-aware Reward for Deep Reinforcement Learning in Human-AI Coordinationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Partner-Aware Hierarchical Skill Discovery for Robust Human-AI Collaboration
  2. 2025CooT: Learning to Coordinate In-Context with Coordination Transformers
  3. 2025Implicitly Aligning Humans and Autonomous Agents through Shared Task Abstractions
  4. 2025Learning "Partner-Aware" Collaborators in Multi-Party Collaboration
  5. 2025Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination
  6. 2025Unsupervised Partner Design Enables Robust Ad-hoc Teamwork
  7. 2022Human-AI Coordination via Human-Regularized Search and Learning
  8. 2024Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning