Learning Structured Communication for Multi-agent Reinforcement Learning

2020-02-11 · Junjie Sheng, Xiangfeng Wang, Bo Jin, Junchi Yan, Wenhao Li, Tsung-Hui Chang, Jun Wang, Hongyuan Zha

This work explores the large-scale multi-agent communication mechanism under a multi-agent reinforcement learning (MARL) setting. We summarize the general categories of topology for communication structures in MARL literature, which are often manually specified. Then we propose a novel framework termed as Learning Structured Communication (LSC) by using a more flexible and efficient communication topology. Our framework allows for adaptive agent grouping to form different hierarchical formations over episodes, which is generated by an auxiliary task combined with a hierarchical routing protocol. Given each formed topology, a hierarchical graph neural network is learned to enable effective message information generation and propagation among inter- and intra-group communications. In contrast to existing communication mechanisms, our method has an explicit while learnable design for hierarchical communication. Experiments on challenging tasks show the proposed LSC enjoys high communication efficiency, scalability, and global cooperation capability.

📄 PDF Abstract BibTeX arXiv:2002.04235

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Neural Network Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음

Pragmatic Reasoning in Structured Signaling Games

2023-05-17 · Emil Carlsson, Devdatt Dubhashi

In this work we introduce a structured signaling game, an extension of the classical signaling game with a similarity structure between meanings in the context, along with a variant of the Rational Speech Act (RSA) frame…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning

Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input

2018-04-11 · ICLR 2018 1 · Angeliki Lazaridou, Karl Moritz Hermann, Karl Tuyls, Stephen Clark

The ability of algorithms to evolve or learn (compositional) communication protocols has traditionally been studied in the language evolution literature through the use of emergent communication tasks. Here we scale up t…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Learning Multi-Agent Communication through Structured Attentive Reasoning

2020-12-01 · NeurIPS 2020 12 · Murtaza Rangwala, Ryan Williams

Learning communication via deep reinforcement learning has recently been shown to be an effective way to solve cooperative multi-agent tasks. However, learning which communicated information is beneficial for each agent'…

Decision Making Deep Reinforcement Learning Multi-agent Reinforcement Learning Policy Gradient Methods+2

Frequency-Based Patrolling with Heterogeneous Agents and Limited Communication

2014-02-07 · Tao Mao, Laura Ray

This paper investigates multi-agent frequencybased patrolling of intersecting, circle graphs under conditions where graph nodes have non-uniform visitation requirements and agents have limited ability to communicate. The…

Reinforcement Learning

HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning

2026-06-28 · Runze Zhao, Dongruo Zhou, Sumit Kumar Jha, Nathaniel D. Bastian 외 arxiv

Cooperative multi-agent reinforcement learning (MARL) often relies on communication to mitigate partial observability, yet most existing protocols treat messages as flat dense vectors detached from the structure of the o…

Multi-agent Reinforcement Learning Information Retrieval