Context-aware Communication for Multi-agent Reinforcement Learning

2023-12-25 · Xinran Li, Jun Zhang

Effective communication protocols in multi-agent reinforcement learning (MARL) are critical to fostering cooperation and enhancing team performance. To leverage communication, many previous works have proposed to compress local information into a single message and broadcast it to all reachable agents. This simplistic messaging mechanism, however, may fail to provide adequate, critical, and relevant information to individual agents, especially in severely bandwidth-limited scenarios. This motivates us to develop context-aware communication schemes for MARL, aiming to deliver personalized messages to different agents. Our communication protocol, named CACOM, consists of two stages. In the first stage, agents exchange coarse representations in a broadcast fashion, providing context for the second stage. Following this, agents utilize attention mechanisms in the second stage to selectively generate messages personalized for the receivers. Furthermore, we employ the learned step size quantization (LSQ) technique for message quantization to reduce the communication overhead. To evaluate the effectiveness of CACOM, we integrate it with both actor-critic and value-based MARL algorithms. Empirical results on cooperative benchmark tasks demonstrate that CACOM provides evident performance gains over baselines under communication-constrained scenarios. The code is publicly available at https://github.com/LXXXXR/CACOM.

📄 PDF Abstract BibTeX arXiv:2312.15600

Code (1)

lxxxxr/cacom 공식 구현 pytorch

Tasks

Multi-agent Reinforcement Learning Quantization reinforcement-learning Reinforcement Learning

Contextual Knowledge Sharing in Multi-Agent Reinforcement Learning with Decentralized Communication and Coordination

2025-01-26 · Hung Du, Srikanth Thudumu, Hy Nguyen, Rajesh Vasa 외

Decentralized Multi-Agent Reinforcement Learning (Dec-MARL) has emerged as a pivotal approach for addressing complex tasks in dynamic environments. Existing Multi-Agent Reinforcement Learning (MARL) methodologies typical…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning

DACOM: Learning Delay-Aware Communication for Multi-Agent Reinforcement Learning

2022-12-03 · Tingting Yuan, Hwei-Ming Chung, Jie Yuan, XiaoMing Fu

Communication is supposed to improve multi-agent collaboration and overall performance in cooperative Multi-agent reinforcement learning (MARL). However, such improvements are prevalently limited in practice since most e…

Autonomous Driving Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Safe Heterogeneous Multi-Agent RL with Communication Regularization for Coordinated Target Acquisition

2026-01-13 · Gabriele Calzolari, Vidya Sumathy, Christoforos Kanellakis, George Nikolakopoulos arxiv

This paper introduces a decentralized multi-agent reinforcement learning framework enabling structurally heterogeneous teams of agents to jointly discover and acquire randomly located targets in environments characterize…

Multi-agent Reinforcement Learning Collision Avoidance

LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning

2026-05-18 · Sangjun Bae, Yisak Park, Sanghyeon Lee, Seungyul Han arxiv

Communication is a key component in multi-agent reinforcement learning (MARL) for mitigating partial observability, yet prior approaches often rely on inefficient information exchange or fail to transmit sufficient state…

Multi-agent Reinforcement Learning

Toward Multi-Agent Reinforcement Learning for Distributed Event-Triggered Control

2023-05-15 · Lukas Kesper, Sebastian Trimpe, Dominik Baumann

Event-triggered communication and control provide high control performance in networked control systems without overloading the communication network. However, most approaches require precise mathematical models of the s…