arXiv AI

SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation

SIGMA is a hierarchical framework for cooperative multi‑agent reinforcement learning that addresses structured noise effects—local correlations in noise-induced decision impacts among agents with strong task dependencies. It groups agents into adaptive local structures using density‑based clustering, aggregates intra‑group representations to smooth deviations, and then applies inter‑group attention to integrate information while respecting heterogeneous contributions. Experiments on noisy‑observation StarCraft II tasks confirm that SIGMA improves robustness to observation noise without sacrificing performance in clean environments.

arXiv AI
Jul 7

Multi-Robot Open Adaptive Teaming Across Unseen Environments, Partners, and Scales

arXiv:2607. 04972v1 Announce Type: cross Abstract: Deploying robot teams in the real world requires simultaneous adaptation to unseen environments, unknown partners, and varying team sizes, yet existing approaches often address these challenges in isolation under the closed-world assumption of fixed teammates.

By Yang Li, Feng Xue, Fan Mo, Yunhao Liu, Jianhong Wang, Ying Wen, Qingrui Zhang, Shaoshuai Mou, Wei Pan
arXiv AI
Oct 19

Coordination Matters: Process-Aware Evaluation of Cooperative Multi-Agent Reinforcement Learning

The paper introduces a process‑aware evaluation framework for cooperative multi‑agent reinforcement learning that supplements traditional outcome metrics with diagnostics of interference, coordinated task completion, participation, and coordination efficiency. Using the STAT testbed and two established benchmarks, the authors demonstrate that policies with similar returns can differ markedly in coordination behavior, and that reward shaping can alter coordination without affecting overall task return. The framework reveals distinct process signatures across spatial, task, and agent scaling and remains informative across different coordination mechanisms.

By Maria Ana Cardei, Matthew Landers, Afsaneh Doryab
arXiv Machine Learning
Oct 28

Preference-Guided Cooperation in Multi-Objective Multi-Agent Reinforcement Learning

The paper introduces Meta-Gradient Informed Multi-Objective Multi-Agent Reinforcement Learning (MIRL), a framework that leverages the structure of multiple objectives to enhance cooperation among agents. By formulating MOMARL at both team and individual levels and using objective-wise counterfactual credit assignment, MIRL allows agents to learn how to prioritize objectives individually while jointly optimizing a system-level objective. Experiments on a multi-objective particle environment demonstrate that MIRL, especially its dynamic variant, improves Pareto-front quality compared to baseline methods.

By Qiyue Xia, J. Michael Herrmann
arXiv Machine Learning
Jul 21

Value-Aware Prediction for Robust Multi-Agent Coordination Under Communication Loss

arXiv:2607. 17914v1 Announce Type: cross Abstract: Robust multi-agent coordination relies heavily on inter-agent communication, which is frequently disrupted by physical and environmental constraints in real-world deployments.

By Kemal Devrim Kafadar, Eren \"Ozaltun, Mahmud Efnan \c{S}anl{\i}, Feyza Orak, Emirhan Gazi, Kubilay Ka\u{g}an K\"om\"urc\"u, Naz{\i}m Kemal \"Ure
arXiv AI
Jun 30

Learned Coordination Conventions in Cooperative MARL: Measuring the Translation Gap Between Theory-Informed Roles and Learned Routing

arXiv:2606. 29541v1 Announce Type: new Abstract: Role-semantic assignments provide priors over how heterogeneous agents may coordinate, but cooperative MARL systems instead settle on conventions through decentralized, non-stationary learning, with no guarantee that the resulting structure matches those priors.

By Yoosung Hong
Hugging Face Trending Papers
Jun 28

Learned Coordination Conventions in Cooperative MARL: Measuring the Translation Gap Between Theory-Informed Roles and Learned Routing

Role-semantic assignments provide priors over how heterogeneous agents may coordinate, but cooperative MARL systems instead settle on conventions through decentralized, non-stationary learning, with no guarantee that the resulting structure matches those priors. We study this translation gap between theory-informed role expectations and learned coordination structure through a diagnostic combining a role-routing matrix, formation sensitivity ($Δ_{\max}$), and gradient/occlusion attribution across three-role MiniGrid and SMACv2 (Terran) environments.

arXiv AI
Sep 11

ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork

The paper introduces ROTATE, a regret-driven open‑ended training framework that jointly improves an Ad Hoc Teamwork (AHT) agent and an adversarial teammate generator. Unlike traditional two‑stage pipelines, ROTATE alternates between enhancing the agent and generating teammates that specifically probe its collaboration weaknesses. Experiments on Overcooked and Level‑Based Foraging show that ROTATE outperforms existing baselines on unseen teammates, setting a new benchmark for robust, generalizable teamwork.

By Caroline Wang, Arrasy Rahman, Benjamin Nativi, Jiaxun Cui, Yoonchang Sung, Peter Stone