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 outperform

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychan2025padiff

Related papers

• Generating Teammates For Training Robust Ad Hoc Teamwork Agents Via Best-response Diversity (2022)0.00
• Modelling The Dynamic Joint Policy Of Teammates With Attention Multi-agent DDPG (2018)5.84
• Madiff: Offline Multi-agent Learning With Diffusion Models (2023)2.26
• Zero-shot Coordination In Ad Hoc Teams With Generalized Policy Improvement And Difference Rewards (2025)0.00
• Delay-aware Diffusion Policy: Bridging The Observation-execution Gap In Dynamic Tasks (2025)0.00
• Diwa: Diffusion Policy Adaptation With World Models (2025)0.00
• Fast Teammate Adaptation In The Presence Of Sudden Policy Change (2023)0.00
• Diffusion Policy Through Conditional Proximal Policy Optimization (2026)0.00