CoDiMAD: Diffusion-Based Privileged Distillation for Communication-Free Multi-Robot Coordination

• URL: http://arxiv.org/abs/2607.09587v1
• Date: Fri, 10 Jul 2026 16:36:45 GMT
• Title: CoDiMAD: Diffusion-Based Privileged Distillation for Communication-Free Multi-Robot Coordination
• Abstract summary: CoDiMAD is a framework that trains a privileged oracle with MAPPO and distills the oracle into decentralized students.<n> Experiments on three cooperative tasks show that CoDiMAD consistently outperforms direct local MARL and deterministic distillation baselines.
• Score: 2.17870369215002
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Decentralized multi-robot coordination under partial observability remains challenging, especially in communication-free settings where agents must act solely from local sensor observations. Privileged policy distillation provides a promising approach by transferring knowledge from a globally informed oracle to sensor-constrained students. However, in multi-agent systems, the same local observation may correspond to multiple global configurations requiring qualitatively different cooperative actions, making the conditional action distribution inherently multi-modal. Standard deterministic distillation collapses these modes to their mean, often yielding invalid or hesitant actions. To address this issue, we propose CoDiMAD, a three-stage framework that trains a privileged oracle with MAPPO, constructs an offline dataset of local-observation-oracle-action pairs, and distills the oracle into decentralized students parameterized as conditional denoising diffusion probabilistic models. By approximating the conditional oracle-action distribution through the diffusion reverse process, CoDiMAD samples decisive actions from coherent coordination modes rather than averaging across them. Theoretical analysis characterizes the mode-averaging failure of deterministic distillation and the distributional recovery property of diffusion-based distillation. Experiments on three cooperative tasks show that CoDiMAD consistently outperforms direct local MARL and deterministic distillation baselines. The source code will be made publicly available upon acceptance.

Related papers

• From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search [12.160113054571356]
  Agentic search enables large language models to solve knowledge-intensive tasks by interleaving multi-step reasoning with retrieval.<n>Knowledge distillation can supply guidance, and advanced proprietary models with their strong reasoning capabilities are promising teachers.<n>We propose Multi-Agent Protocol Distillation (MAPD), a joint distillation and outcome-based reinforcement learning framework.
  arXiv  Detail & Related papers  (2026-07-27T11:27:38Z)
• Structural Equivalence and Learning Dynamics in Delayed MARL [2.2302915692528367]
  We establish the equivalence between Observation Delay (OD) and Action Delay (AD) in cooperative partially observable multi-agent systems.<n>We show that both systems generate identical admissible joint-policy sets and their induced state-action-observation trajectories are identical in distribution.<n>This formally generalizes existing infinite-horizon single-agent results to any-horizon partially observable cooperative multi-agent problems.
  arXiv  Detail & Related papers  (2026-05-05T23:07:09Z)
• Omnimodal Dataset Distillation via High-order Proxy Alignment [59.74134776126595]
  We propose HoPA, a unified method that captures high-order cross-modal alignments via a proxy structure.<n>Our method avoids the complexity of pairwise modality modeling and enables scalable proxy analysis across heterogeneous modalities.
  arXiv  Detail & Related papers  (2026-04-12T14:47:41Z)
• COP-GEN: Latent Diffusion Transformer for Copernicus Earth Observation Data -- Generation Stochastic by Design [9.278432103577925]
  Earth observation applications increasingly rely on data from multiple sensors, including optical, radar, elevation, and land-cover products.<n>We introduce COP-GEN, a latent diffusion transformer that models the joint distribution of heterogeneous Earth Observation modalities at their native spatial resolutions.<n>Experiments on a large-scale global multimodal dataset show that COP-GEN generates diverse yet physically consistent realisations while maintaining strong peak fidelity across optical, radar, and elevation modalities.
  arXiv  Detail & Related papers  (2026-03-03T18:31:46Z)
• Distillation of Discrete Diffusion by Exact Conditional Distribution Matching [9.460409527892345]
  We propose a simple and principled distillation alternative based on emphconditional distribution matching.<n>We exploit this structure to define distillation objectives that directly match conditional distributions between a pre-trained teacher and a low-NFE student.
  arXiv  Detail & Related papers  (2025-12-15T00:16:10Z)
• Locality Preserving Markovian Transition for Instance Retrieval [59.16243976912006]
  We introduce the Locality Preserving Markovian Transition (LPMT) framework, which employs a long-term thermodynamic transition process with multiple states for accurate manifold distance measurement.<n>The proposed LPMT first integrates diffusion processes across separate graphs using Bidirectional Collaborative Diffusion (BCD) to establish strong similarity relationships.<n>After, Locality State Embedding (LSE) encodes each instance into a distribution for enhanced local consistency.<n>These distributions are interconnected via the Thermodynamic Markovian Transition (TMT) process, enabling efficient global retrieval while maintaining local effectiveness.
  arXiv  Detail & Related papers  (2025-06-05T16:07:31Z)
• Collaborative Value Function Estimation Under Model Mismatch: A Federated Temporal Difference Analysis [55.13545823385091]
  Federated reinforcement learning (FedRL) enables collaborative learning while preserving data privacy by preventing direct data exchange between agents.<n>In real-world applications, each agent may experience slightly different transition dynamics, leading to inherent model mismatches.<n>We show that even moderate levels of information sharing significantly mitigate environment-specific errors.
  arXiv  Detail & Related papers  (2025-03-21T18:06:28Z)
• Counterfactual Realizability [52.85109506684737]
  We introduce a formal definition of realizability, the ability to draw samples from a distribution, and then develop a complete algorithm to determine whether an arbitrary counterfactual distribution is realizable.<n>We illustrate the implications of this new framework for counterfactual data collection using motivating examples from causal fairness and causal reinforcement learning.
  arXiv  Detail & Related papers  (2025-03-14T20:54:27Z)
• On Diffusion Models for Multi-Agent Partial Observability: Shared Attractors, Error Bounds, and Composite Flow [37.433470342139685]
  We investigate reconstructing global states from local action-observation histories in Dec-POMDPs using diffusion models.<n>We find that, with deep learning approximation errors, fixed points can deviate from true states and the deviation is negatively correlated to the Jacobian rank.
  arXiv  Detail & Related papers  (2024-10-17T18:23:33Z)
• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional dependencies for general score-mismatched diffusion samplers.<n>We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions.<n>This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• Decentralized Local Stochastic Extra-Gradient for Variational Inequalities [125.62877849447729]
  We consider distributed variational inequalities (VIs) on domains with the problem data that is heterogeneous (non-IID) and distributed across many devices. We make a very general assumption on the computational network that covers the settings of fully decentralized calculations. We theoretically analyze its convergence rate in the strongly-monotone, monotone, and non-monotone settings.
  arXiv  Detail & Related papers  (2021-06-15T17:45:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.