PADiff: Predictive and Adaptive Diffusion Policies for Ad Hoc Teamwork

TL;DR

PADiff introduces a diffusion-based method for ad hoc teamwork that captures multimodal cooperation behaviors and adapts to unknown teammates, significantly outperforming existing approaches in diverse environments.

Contribution

The paper presents PADiff, a novel diffusion-based policy that models multimodal behaviors and incorporates predictive information for adaptive ad hoc teamwork.

Findings

PADiff outperforms existing AHT methods across three environments.

The diffusion approach captures diverse cooperation modes effectively.

Incorporating predictive information enhances adaptability in non-stationary scenarios.

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.