# MIMIC-D: Multi-modal Imitation for MultI-agent Coordination with Decentralized Diffusion Policies

arXiv: https://arxiv.org/abs/2509.14159 · HTML: https://mlsanity.com/paper/2509.14159/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 31 of its 40 references that are in the map.
- First posted on arXiv 17 Sep 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 30 of 31)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion](https://mlsanity.com/paper/2306.03083/) (2023)
- [A Survey and Critique of Multiagent Deep Reinforcement Learning](https://mlsanity.com/paper/1810.05587/) (2018)
- [Multi-Agent Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1807.09936/) (2018)
- [Robust Imitation of Diverse Behaviors](https://mlsanity.com/paper/1707.02747/) (2017)
- [MADiff: Offline Multi-agent Learning with Diffusion Models](https://mlsanity.com/paper/2305.17330/) (2023)
- [Multi-Agent Imitation Learning for Driving Simulation](https://mlsanity.com/paper/1803.01044/) (2018)
- [Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularization](https://mlsanity.com/paper/2111.07999/) (2021)
- [Maximum-Entropy Multi-Agent Dynamic Games: Forward and Inverse Solutions](https://mlsanity.com/paper/2110.01027/) (2021)
- [Leveraging Large Language Models for Effective and Explainable Multi-Agent Credit Assignment](https://mlsanity.com/paper/2502.16863/) (2025)
- [A Diffusion-Model of Joint Interactive Navigation](https://mlsanity.com/paper/2309.12508/) (2023)
- [Inference-Based Strategy Alignment for General-Sum Differential Games](https://mlsanity.com/paper/2002.04354/) (2020)
- [Latent Theory of Mind: A Decentralized Diffusion Architecture for Cooperative Manipulation](https://mlsanity.com/paper/2505.09144/) (2025)
- [Potential iLQR: A Potential-Minimizing Controller for Planning Multi-Agent Interactive Trajectories](https://mlsanity.com/paper/2107.04926/) (2021)
- [Multi-Agent Inverse Reinforcement Learning in Real World Unstructured Pedestrian Crowds](https://mlsanity.com/paper/2405.16439/) (2024)
- [Geometric Impedance Control on SE(3) for Robotic Manipulators](https://mlsanity.com/paper/2211.07945/) (2022)
- [MisoDICE: Multi-Agent Imitation from Unlabeled Mixed-Quality Demonstrations](https://mlsanity.com/paper/2505.18595/) (2025)
- [Strategic Decision-Making in Multi-Agent Domains: A Weighted Constrained Potential Dynamic Game Approach](https://mlsanity.com/paper/2308.05876/) (2023)

## Built on by (most cited first, 7 of 7)

- [CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA Policy](https://mlsanity.com/paper/2606.12352/) (2026)
- [Simulation-Informed Diffusion for Decentralized Multi-robot Motion Planning](https://mlsanity.com/paper/2605.27697/) (2026)
- [X-Safe: Embodiment-Agnostic Safeguarding for Robot Arm Manipulation Policies via Action Masking](https://mlsanity.com/paper/2606.22278/) (2026)
- [CoHuB: A Simulation Benchmark for Multi-Humanoid Collaboration](https://mlsanity.com/paper/2609.34782/) (2026)
- [DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communication](https://mlsanity.com/paper/2610.02161/) (2026)
- [Watch, Infer, Coordinate: Inferring Robot Partner Constraints for Zero-Shot Coordination](https://mlsanity.com/paper/2610.02170/) (2026)
- [CoLA: Multi-VLA Coordination via Learned Adapters](https://mlsanity.com/paper/2610.15337/) (2026)

## Abstract (arXiv)

As robots become more integrated in society, their ability to coordinate with other robots and humans on multi-modal tasks (those with multiple valid solutions) is crucial. Such behaviors can be learned from expert demonstrations via imitation learning (IL), but when expert demonstrations are multi-modal, standard IL approaches usually average across modes or collapse to a single mode, preventing effective coordination. Being inspired by diffusion models' ability to capture complex multi-modal trajectory distributions in single-agent settings, we develop a diffusion-based framework for coordinated multi-modal behavior in multi-agent systems. However, existing multi-agent diffusion approaches typically require a centralized planner or explicit communication among agents. This assumption can fail in real-world scenarios where robots must operate independently or with agents like humans that they cannot directly communicate with. Therefore, we propose MIMIC-D, a joint training with decentralized execution paradigm for multi-modal multi-agent IL via diffusion. We jointly train all agents' policies with only local information to achieve implicit coordination. In simulation and hardware experiments, our method exhibits robust multi-modal coordination behavior in various tasks and environments, improving upon state-of-the-art baselines.