mlsanityData to 14 Oct 2026

PADiff: Predictive and Adaptive Diffusion Policies for Ad Hoc Teamwork

arXiv 2511.07260 ↗First posted 10 Nov 2025cs.AI cs.LGcited by 0

On the map: Diffusion models → Diffusion and flow policies for robotics

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 28 of its 47 references that are in the map. First posted on arXiv 10 Nov 2025.

Builds on

28 of 47 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution18 Dec
  2. 2023Diffusion Models for Reinforcement Learning: A Survey2 Nov
  3. 2023MADiff: Offline Multi-agent Learning with Diffusion Models27 May
  4. 2023IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies20 Apr
  5. 2023AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners3 Feb

Other references · 23

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  3. 2022Generative Adversarial Networkscited by 5,627
  4. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  5. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  6. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  7. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  8. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
  9. 2016Generative Adversarial Imitation Learningcited by 1,597
  10. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  11. 2023Mastering Diverse Domains through World Modelscited by 1,253
  12. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
11 more
  1. 2022Diffusion Models in Vision: A Surveycited by 1,015
  2. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 780
  3. 2021Score-based Generative Modeling in Latent Spacecited by 636
  4. 2019Learning Latent Plans from Playcited by 316
  5. 2022What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Datacited by 138
  6. 2020Learning to Generalize Across Long-Horizon Tasks from Human Demonstrationscited by 115
  7. 2020Agent Modelling under Partial Observability for Deep Reinforcement Learningcited by 57
  8. 2023A Survey of Progress on Cooperative Multi-agent Reinforcement Learning in Open Environmentcited by 39
  9. 2020Towards Open Ad Hoc Teamwork Using Graph-based Policy Learningcited by 37
  10. 2021Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Taskscited by 32
  11. 2023Future-conditioned Unsupervised Pretraining for Decision Transformercited by 26

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025ToMCAT: Theory-of-Mind for Cooperative Agents in Teams via Multiagent Diffusion Policies
  2. 2026Learning When to Cooperate Under Heterogeneous Goals
  3. 2024N-Agent Ad Hoc Teamwork
  4. 2023Knowledge-based Reasoning and Learning under Partial Observability in Ad Hoc Teamwork
  5. 2026Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork
  6. 2025ReCollab: Retrieval-Augmented LLMs for Cooperative Ad-hoc Teammate Modeling
  7. 2026JaxAHT: A JAX-Based Library for Ad Hoc Teamwork
  8. 2026Residual Denoising Enables Sample-Efficient Multi-Agent Coordination on Demand ↗