# Partner-Aware Hierarchical Skill Discovery for Robust Human-AI Collaboration

arXiv: https://arxiv.org/abs/2605.24352 · HTML: https://mlsanity.com/paper/2605.24352/

## 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 27 references that are in the map.
- First posted on arXiv 23 May 2026.

## Placed in

- Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/)

## Builds on (most cited first, 17 of 17)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Diversity is All You Need: Learning Skills without a Reward Function](https://mlsanity.com/paper/1802.06070/) (2018)
- [On the Utility of Learning about Humans for Human-AI Coordination](https://mlsanity.com/paper/1910.05789/) (2019)
- [FeUdal Networks for Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1703.01161/) (2017)
- [Variational Intrinsic Control](https://mlsanity.com/paper/1611.07507/) (2016)
- ["Other-Play" for Zero-Shot Coordination](https://mlsanity.com/paper/2003.02979/) (2020)
- [The Hanabi Challenge: A New Frontier for AI Research](https://mlsanity.com/paper/1902.00506/) (2019)
- [Collaborating with Humans without Human Data](https://mlsanity.com/paper/2110.08176/) (2021)
- [Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills](https://mlsanity.com/paper/2002.03647/) (2020)
- [Towards Playing Full MOBA Games with Deep Reinforcement Learning](https://mlsanity.com/paper/2011.12692/) (2020)
- [Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination](https://mlsanity.com/paper/2112.11701/) (2021)
- [Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased](https://mlsanity.com/paper/2302.01605/) (2023)
- [Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversity](https://mlsanity.com/paper/2110.04041/) (2021)
- [Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination](https://mlsanity.com/paper/2504.12714/) (2025)
- [A Hierarchical Approach to Population Training for Human-AI Collaboration](https://mlsanity.com/paper/2305.16708/) (2023)
- [BCR-DRL: Behavior- and Context-aware Reward for Deep Reinforcement Learning in Human-AI Coordination](https://mlsanity.com/paper/2408.07877/) (2024)

## Abstract (arXiv)

Multi-agent collaboration, especially in human-AI teaming, requires agents that can adapt to novel partners with diverse and dynamic behaviors. Conventional Deep Hierarchical Reinforcement Learning (DHRL) methods focus on agent-centric rewards and overlook partner behavior, leading to shortcut learning, where skills exploit spurious information instead of adapting to partners' dynamic behaviors. This limitation undermines agents' ability to adapt and coordinate effectively with novel partners. We introduce Partner-Aware Skill Discovery (PASD), a DHRL framework that learns skills conditioned on partner behavior. PASD introduces a contrastive intrinsic reward to capture patterns emerging from partner interactions, aligning skill representations across similar partners while maintaining discriminability across diverse strategies. By structuring the skill space based on partner interactions, this approach mitigates shortcut learning and promotes behavioral consistency, enabling robust and adaptive coordination. We extensively evaluate PASD in the Overcooked-AI benchmark with a diverse population of partners characterized by varying skill levels and play styles. We further evaluate the approach with human proxy models trained from human-human gameplay trajectories. PASD consistently outperforms existing population-based and hierarchical baselines, demonstrating transferable skill learning that generalizes across a wide range of partner behaviors. Analysis of learned skill representations shows that PASD adapts effectively to diverse partner behaviors, highlighting its robustness in human-AI collaboration.