PADiff: Predictive and Adaptive Diffusion Policies for Ad Hoc Teamwork
This work addresses the challenge of developing adaptable agents for real-world collaborative scenarios with unknown teammates, representing a novel method for a known bottleneck.
The paper tackled the problem of ad hoc teamwork where agents must collaborate with unseen teammates, by introducing PADiff, a diffusion-based approach that integrates predictive information to capture multimodal behaviors, resulting in significant outperformance over existing methods in three cooperation environments.
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.