Unsupervised Partner Design Enables Robust Ad-hoc Teamwork
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_ | 1866911098722058240 |
|---|---|
| author | Ruhdorfer, Constantin Bortoletto, Matteo Oei, Victor Penzkofer, Anna Bulling, Andreas |
| author_facet | Ruhdorfer, Constantin Bortoletto, Matteo Oei, Victor Penzkofer, Anna Bulling, Andreas |
| contents | We introduce Unsupervised Partner Design (UPD) - a population-free, multi-agent reinforcement learning framework for robust ad-hoc teamwork that adaptively generates training partners without requiring pretrained partners or manual parameter tuning. UPD constructs diverse partners by stochastically mixing an ego agent's policy with biased random behaviours and scores them using a variance-based learnability metric that prioritises partners near the ego agent's current learning frontier. We show that UPD can be integrated with unsupervised environment design, resulting in the first method enabling fully unsupervised curricula over both level and partner distributions in a cooperative setting. Through extensive evaluations on Overcooked-AI and the Overcooked Generalisation Challenge, we demonstrate that this dynamic partner curriculum is highly effective: UPD consistently outperforms both population-based and population-free baselines as well as ablations. In a user study, we further show that UPD achieves higher returns than all baselines and was perceived as significantly more adaptive, more human-like, a better collaborator, and less frustrating. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_06336 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unsupervised Partner Design Enables Robust Ad-hoc Teamwork Ruhdorfer, Constantin Bortoletto, Matteo Oei, Victor Penzkofer, Anna Bulling, Andreas Machine Learning Artificial Intelligence Human-Computer Interaction Multiagent Systems We introduce Unsupervised Partner Design (UPD) - a population-free, multi-agent reinforcement learning framework for robust ad-hoc teamwork that adaptively generates training partners without requiring pretrained partners or manual parameter tuning. UPD constructs diverse partners by stochastically mixing an ego agent's policy with biased random behaviours and scores them using a variance-based learnability metric that prioritises partners near the ego agent's current learning frontier. We show that UPD can be integrated with unsupervised environment design, resulting in the first method enabling fully unsupervised curricula over both level and partner distributions in a cooperative setting. Through extensive evaluations on Overcooked-AI and the Overcooked Generalisation Challenge, we demonstrate that this dynamic partner curriculum is highly effective: UPD consistently outperforms both population-based and population-free baselines as well as ablations. In a user study, we further show that UPD achieves higher returns than all baselines and was perceived as significantly more adaptive, more human-like, a better collaborator, and less frustrating. |
| title | Unsupervised Partner Design Enables Robust Ad-hoc Teamwork |
| topic | Machine Learning Artificial Intelligence Human-Computer Interaction Multiagent Systems |
| url | https://arxiv.org/abs/2508.06336 |