{"ID":2844053,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.07260","arxiv_id":"2511.07260","title":"PADiff: Predictive and Adaptive Diffusion Policies for Ad Hoc Teamwork","abstract":"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.","short_abstract":"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, w...","url_abs":"https://arxiv.org/abs/2511.07260","url_pdf":"https://arxiv.org/pdf/2511.07260v2","authors":"[\"Hohei Chan\",\"Xinzhi Zhang\",\"Antao Xiang\",\"Weinan Zhang\",\"Mengchen Zhao\"]","published":"2025-11-10T16:05:40Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.LG\"]","methods":"[\"Diffusion Model\"]","has_code":false}