MARL
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Modelling Opinion Dynamics at Scale with Deep MARL
arXiv:2606.07487v1 Announce Type: new Abstract: Modelling opinion dynamics typically relies on hand-crafted local interaction rules to study emergent macroscopic phenomena such as consensus and polarisation. In contrast, multi-agent reinforcement learning (MARL) enables agents to learn such behaviours directly by optimising simple rewards. To explore the potential of MARL for opinion dynamics, we introduce a GPU-accelerated consensus and truth-finding game that scales to populations of up to...
Learning Multi-Agent Communication Protocol: Study on Information Entropy Efficiency in MARL
arXiv:2606.07200v1 Announce Type: new Abstract: Multi-Agent Systems (MAS) have emerged as a fundamental paradigm for distributed problem-solving, where autonomous agents collaborate to achieve complex objectives. Within this framework, Multi-Agent Reinforcement Learning (MARL) with communication has demonstrated remarkable success in cooperative tasks. However, existing approaches predominantly pursue performance gains through increasingly complex architectures and expanding communication...
Learning to Contest: Decentralized Robust Fairness in Cooperative MARL via Cross-Attention
arXiv:2606.06162v1 Announce Type: new Abstract: Fair cooperative multi-agent RL (MARL) teams maximizing egalitarian welfare are exploitable: a single selfish agent free-rides on the surplus fair agents forgo to raise the worst-off. A centralized need-based allocator removes it, but only by taking allocation out of agents' hands; whether decentralized policies can be robust was left open.
New Aukus drone subs to protect critical undersea cables as Marles warns: ‘seabed is a battlefield’
Minister at Singapore defence summit also reveals Australia to buy only second-hand Aukus submarines from USGet our breaking news email, free app or daily news podcastThe defence minister, Richard Marles, has said the “seabed is a battlefield” in a combative speech urging Beijing to be more transparent about its maritime operations, and taking aim at weak international controls over so-called “shadow-fleet” vessels. The warning came as the US, UK and Australia announced a new Aukus project...
Provably Convergent Actor-Critic for MARL through Risk-aversion
arXiv:2602.12386v2 Announce Type: replace Abstract: Learning stationary policies in infinite-horizon general-sum Markov games (MGs) remains a fundamental open problem in Multi-Agent Reinforcement Learning (MARL). While stationary strategies are preferred for their practicality, computing stationary forms of classic game-theoretic equilibria is computationally intractable -- a stark contrast to the comparative ease of solving single-agent RL or zero-sum games. To bridge this gap, we study...
New Aukus drone subs to protect critical undersea cables as Marles warns: ‘seabed is a battlefield’
Minister at Singapore defence summit also reveals Australia to buy only secondhand Aukus submarines from USFollow our Australia news live blog for latest updatesGet our breaking news email, free app or daily news podcastThe defence minister, Richard Marles, has said the “seabed is a battlefield” in a combative speech urging Beijing to be more transparent about its maritime operations, and taking aim at weak international controls over so-called “shadow-fleet” vessels. The warning came as the...
A Unified Framework for Locality in Scalable MARL
arXiv:2602.16966v2 Announce Type: replace Abstract: Scalable methods for networked multi-agent reinforcement learning let each agent plan using only a small neighborhood of the agent graph. This works only when the system is value-local, meaning a perturbation at one agent affects the long-run value at another agent weakly when the two are far apart. In the average-reward setting, the standard way to certify locality is the Dobrushin row-sum bound on a single matrix $C^\pi$ that captures how...
Mean-Field Diffuser: Scaling Offline MARL to Thousands of Agents
arXiv:2605.30190v2 Announce Type: replace Abstract: Diffusion-based planning has achieved strong results in single-agent offline reinforcement learning, yet scaling to many-agent systems remains intractable due to the curse of dimensionality in the joint trajectory space. We introduce MF-Diffuser, a framework that lifts trajectory planning to the Wasserstein space of trajectory distributions, where the propagation of chaos ensures a small representative subset of agents captures the full...