MACTAS: Self-Attention-Based Module for Inter-Agent Communication in Multi-Agent Reinforcement Learning

• URL: http://arxiv.org/abs/2508.13661v2
• Date: Wed, 15 Oct 2025 13:19:58 GMT
• Title: MACTAS: Self-Attention-Based Module for Inter-Agent Communication in Multi-Agent Reinforcement Learning
• Authors: Maciej Wojtala, Bogusz Stefańczyk, Dominik Bogucki, Łukasz Lepak, Jakub Strykowski, Paweł Wawrzyński,
• Abstract summary: We introduce a self-attention-based communication module that exchanges information between the agents in MARL.<n>Our proposed approach is fully differentiable, allowing agents to learn to generate messages in a reward-driven manner.<n> Experimental results on the SMAC and SMACv2 benchmarks demonstrate the effectiveness of our approach.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Communication is essential for the collective execution of complex tasks by human agents, motivating interest in communication mechanisms for multi-agent reinforcement learning (MARL). However, existing communication protocols in MARL are often complex and non-differentiable. In this work, we introduce a self-attention-based communication module that exchanges information between the agents in MARL. Our proposed approach is fully differentiable, allowing agents to learn to generate messages in a reward-driven manner. The module can be seamlessly integrated with any action-value function decomposition method and can be viewed as an extension of such decompositions. Notably, it includes a fixed number of trainable parameters, independent of the number of agents. Experimental results on the SMAC and SMACv2 benchmarks demonstrate the effectiveness of our approach, which achieves state-of-the-art performance on a number of maps.

Related papers

• MARTI-MARS$^2$: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation [64.2621682259008]
  Multi-Agent Reinforced Training and Inference Framework with Self-Search Scaling (MARTI-MARS2)<n>We propose a Multi-Agent Reinforced Training and Inference Framework with Self-Search Scaling (MARTI-MARS2) to integrate policy learning with multi-agent tree search.<n>We show that MARTI-MARS2 achieves 77.7%, outperforming strong baselines like GPT-5.1 on challenging code generation benchmarks.
  arXiv  Detail & Related papers  (2026-02-08T07:28:44Z)
• MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning [53.37068897861388]
  MedSAM-Agent is a framework that reformulates interactive segmentation as a multi-step autonomous decision-making process.<n>We develop a two-stage training pipeline that integrates multi-turn, end-to-end outcome verification.<n>Experiments across 6 medical modalities and 21 datasets demonstrate that MedSAM-Agent achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-03T09:47:49Z)
• Graft: Integrating the Domain Knowledge via Efficient Parameter Synergy for MLLMs [56.76586846269894]
  Multimodal Large Language Models (MLLMs) have achieved success across various domains.<n>Despite its importance, the study of knowledge sharing among domain-specific MLLMs remains largely underexplored.<n>We propose a unified parameter integration framework that enables modular composition of expert capabilities.
  arXiv  Detail & Related papers  (2025-06-30T15:07:41Z)
• AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction [77.62279834617475]
  We propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure.<n>Our method focuses on two key directions: (1) Next-Agent Prediction, which selects the most suitable agent role at each step, and (2) Next-Context Selection, which enables each agent to selectively access relevant information from any previous step.
  arXiv  Detail & Related papers  (2025-06-21T18:34:43Z)
• Verco: Learning Coordinated Verbal Communication for Multi-agent Reinforcement Learning [42.27106057372819]
  We propose a novel multi-agent reinforcement learning algorithm that embeds large language models into agents. The framework has a message module and an action module. Experiments conducted on the Overcooked game demonstrate our method significantly enhances the learning efficiency and performance of existing methods.
  arXiv  Detail & Related papers  (2024-04-27T05:10:33Z)
• Fully Independent Communication in Multi-Agent Reinforcement Learning [4.470370168359807]
  Multi-Agent Reinforcement Learning (MARL) comprises a broad area of research within the field of multi-agent systems. We investigate how independent learners in MARL that do not share parameters can communicate. Our results show that, despite the challenges, independent agents can still learn communication strategies following our method.
  arXiv  Detail & Related papers  (2024-01-26T18:42:01Z)
• T2MAC: Targeted and Trusted Multi-Agent Communication through Selective Engagement and Evidence-Driven Integration [15.91335141803629]
  We propose Targeted and Trusted Multi-Agent Communication (T2MAC) to help agents learn selective engagement and evidence-driven integration. T2MAC enables agents to craft individualized messages, pinpoint ideal communication windows, and engage with reliable partners. We evaluate our method on a diverse set of cooperative multi-agent tasks, with varying difficulties, involving different scales.
  arXiv  Detail & Related papers  (2024-01-19T18:00:33Z)
• MADiff: Offline Multi-agent Learning with Diffusion Models [79.18130544233794]
  MADiff is a diffusion-based multi-agent learning framework.<n>It works as both a decentralized policy and a centralized controller.<n>Our experiments demonstrate that MADiff outperforms baseline algorithms across various multi-agent learning tasks.
  arXiv  Detail & Related papers  (2023-05-27T02:14:09Z)
• Scalable Communication for Multi-Agent Reinforcement Learning via Transformer-Based Email Mechanism [9.607941773452925]
  Communication can impressively improve cooperation in multi-agent reinforcement learning (MARL) We propose a novel framework Transformer-based Email Mechanism (TEM) to tackle the scalability problem of MARL communication for partially-observed tasks.
  arXiv  Detail & Related papers  (2023-01-05T05:34:30Z)
• Centralized Training with Hybrid Execution in Multi-Agent Reinforcement Learning [7.163485179361718]
  We introduce hybrid execution in multi-agent reinforcement learning (MARL) MARL is a new paradigm in which agents aim to successfully complete cooperative tasks with arbitrary communication levels at execution time. We contribute MARO, an approach that makes use of an auto-regressive predictive model, trained in a centralized manner, to estimate missing agents' observations.
  arXiv  Detail & Related papers  (2022-10-12T14:58:32Z)
• Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel [81.39444892747512]
  In Multi-Agent Reinforcement Learning (MARL), specialized channels are often introduced that allow agents to communicate directly with one another. We propose an alternative approach whereby agents communicate through an intelligent facilitator that learns to sift through and interpret signals provided by all agents to improve the agents' collective performance.
  arXiv  Detail & Related papers  (2022-05-21T14:11:33Z)
• A Survey of Multi-Agent Deep Reinforcement Learning with Communication [2.1461517065527445]
  In the field of multi-agent deep reinforcement learning (MADRL), agents can improve the overall learning performance by communication. There is a lack of a systematic and structural approach to distinguish and classify existing Comm-MADRL approaches. We propose 9 dimensions along which Comm-MADRL approaches can be analyzed, developed, and compared.
  arXiv  Detail & Related papers  (2022-03-16T22:39:46Z)
• Multi-Agent Imitation Learning with Copulas [102.27052968901894]
  Multi-agent imitation learning aims to train multiple agents to perform tasks from demonstrations by learning a mapping between observations and actions. In this paper, we propose to use copula, a powerful statistical tool for capturing dependence among random variables, to explicitly model the correlation and coordination in multi-agent systems. Our proposed model is able to separately learn marginals that capture the local behavioral patterns of each individual agent, as well as a copula function that solely and fully captures the dependence structure among agents.
  arXiv  Detail & Related papers  (2021-07-10T03:49:41Z)

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.