PADiff: Predictive and Adaptive Diffusion Policies for 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_ | 1866917208941133824 |
|---|---|
| author | Chan, Hohei Zhang, Xinzhi Xiang, Antao Zhang, Weinan Zhao, Mengchen |
| author_facet | Chan, Hohei Zhang, Xinzhi Xiang, Antao Zhang, Weinan Zhao, Mengchen |
| contents | Ad hoc teamwork (AHT) requires agents to collaborate with previously unseen teammates, which is crucial for many real-world applications. The core challenge of AHT is to develop an ego agent that can predict and adapt to unknown teammates on the fly. Conventional RL-based approaches optimize a single expected return, which often causes policies to collapse into a single dominant behavior, thus failing to capture the multimodal cooperation patterns inherent in AHT. In this work, we introduce PADiff, a diffusion-based approach that captures agent's multimodal behaviors, unlocking its diverse cooperation modes with teammates. However, standard diffusion models lack the ability to predict and adapt in highly non-stationary AHT scenarios. To address this limitation, we propose a novel diffusion-based policy that integrates critical predictive information about teammates into the denoising process. Extensive experiments across three cooperation environments demonstrate that PADiff outperforms existing AHT methods significantly. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_07260 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PADiff: Predictive and Adaptive Diffusion Policies for Ad Hoc Teamwork Chan, Hohei Zhang, Xinzhi Xiang, Antao Zhang, Weinan Zhao, Mengchen Artificial Intelligence Machine Learning Ad hoc teamwork (AHT) requires agents to collaborate with previously unseen teammates, which is crucial for many real-world applications. The core challenge of AHT is to develop an ego agent that can predict and adapt to unknown teammates on the fly. Conventional RL-based approaches optimize a single expected return, which often causes policies to collapse into a single dominant behavior, thus failing to capture the multimodal cooperation patterns inherent in AHT. In this work, we introduce PADiff, a diffusion-based approach that captures agent's multimodal behaviors, unlocking its diverse cooperation modes with teammates. However, standard diffusion models lack the ability to predict and adapt in highly non-stationary AHT scenarios. To address this limitation, we propose a novel diffusion-based policy that integrates critical predictive information about teammates into the denoising process. Extensive experiments across three cooperation environments demonstrate that PADiff outperforms existing AHT methods significantly. |
| title | PADiff: Predictive and Adaptive Diffusion Policies for Ad Hoc Teamwork |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2511.07260 |