← Back to all news
arXiv Machine Learning By Sangmin Lee, Youngju Na, Chanmi Lee, Sung-eui Yoon

Multi-Agent Coordination via Support-Preserving Distillation

Read the original on arXiv Machine Learning →

The paper introduces Mode‑Support Semi‑Discrete Optimal Transport (MoSDOT) to address a failure mode in offline multi‑agent reinforcement learning where flow‑based teachers produce conflicting coordination modes. MoSDOT aggregates multimodal replay into a finite mode support with specified capacities and assigns each noise sample to a single mode before teacher training, thereby preventing the teacher from generating samples between valid modes. Experiments on controlled diagnostics and offline MARL benchmarks show that MoSDOT improves endpoint quality and routing consistency, especially on datasets with multimodal joint behavior.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 5

Test-time Multi-agent Coordination by Decomposed Value Gradient Flow

The paper introduces SCOUT, an offline multi-agent reinforcement learning framework that combines a generative behavioral prior with a decomposed value function for test-time action refinement. SCOUT uses optimal unified transport and Stein variational gradient descent to steer behavioral samples toward high-value regions, with the number of transport steps providing adaptive scaling. The authors prove a single-term KL bound on the joint soft-value gap under the individual-global-max principle and demonstrate that SCOUT outperforms existing methods on both discrete and continuous offline MARL benchmarks, including offline-to-online settings.

By Dongsu Lee, Haoran Xu, Amy Zhang
agentsreinforcement-learningmultimodalbenchmarks
More like this →
arXiv Machine Learning
Oct 8

Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts

The paper introduces Δ‑MOPD, a multi‑teacher on‑policy distillation method that transfers each teacher’s logit shift relative to its base policy, re‑anchored at the student’s frozen initialization. Δ‑MOPD is evaluated in two settings: common‑domain composition, where multiple teachers score a single student rollout, and routed‑domain distillation, where prompts are assigned to specialist teachers. Across experiments, Δ‑MOPD outperforms traditional endpoint supervision, especially when teacher signals are combined at a state, achieving higher accuracy and reducing performance gaps in phased routing scenarios.

By Hejian Sang, Zhengze Zhou, Shayan Mohajer Hamidi, Xiaomin Li, Rohit Jain, Alborz Geramifard
efficiencybenchmarks
More like this →