paper-with-me

홈 › Papers

Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks

2024-07-11 · Pu Feng, Junkang Liang, Size Wang, Xin Yu, Xin Ji, Yiting Chen, Kui Zhang, Rongye Shi, Wenjun Wu

In multi-agent reinforcement learning (MARL), the Centralized Training with Decentralized Execution (CTDE) framework is pivotal but struggles due to a gap: global state guidance in training versus reliance on local observations in execution, lacking global signals. Inspired by human societal consensus mechanisms, we introduce the Hierarchical Consensus-based Multi-Agent Reinforcement Learning (HC-MARL) framework to address this limitation. HC-MARL employs contrastive learning to foster a global consensus among agents, enabling cooperative behavior without direct communication. This approach enables agents to form a global consensus from local observations, using it as an additional piece of information to guide collaborative actions during execution. To cater to the dynamic requirements of various tasks, consensus is divided into multiple layers, encompassing both short-term and long-term considerations. Short-term observations prompt the creation of an immediate, low-layer consensus, while long-term observations contribute to the formation of a strategic, high-layer consensus. This process is further refined through an adaptive attention mechanism that dynamically adjusts the influence of each consensus layer. This mechanism optimizes the balance between immediate reactions and strategic planning, tailoring it to the specific demands of the task at hand. Extensive experiments and real-world applications in multi-robot systems showcase our framework's superior performance, marking significant advancements over baselines.

📄 PDF Abstract BibTeX arXiv:2407.08164

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Dialogue Diplomats: An End-to-End Multi-Agent Reinforcement Learning System for Automated Conflict Resolution and Consensus Building

2025-11-20 · Deepak Bolleddu arxiv

Conflict resolution and consensus building represent critical challenges in multi-agent systems, negotiations, and collaborative decision-making processes. This paper introduces Dialogue Diplomats, a novel end-to-end mul…

Multi-agent Reinforcement Learning

Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus

2026-04-15 · Zijian Zhao, Jing Gao, Sen Li arxiv

Cooperative multi-agent reinforcement learning (MARL) is widely used to address large joint observation and action spaces by decomposing a centralized control problem into multiple interacting agents. However, such decom…

Multi-agent Reinforcement LearningDecision MakingStarcraft II

Network Distributed Multi-Agent Reinforcement Learning for Consensus Control of Quadcopters

2026-06-01 · Youssef Mahran, Zeyad Gamal, Aamir Ahmad, Ayman El-Badawy arxiv

This paper proposes a Network Distributed Multi-Agent Reinforcement Learning (ND-MARL) framework for quadcopter consensus control. Compared to conventional multi-agent MARL formulations that rely on centralized planning …

Multi-agent Reinforcement Learning

Structured Diversification Emergence via Reinforced Organization Control and Hierarchical Consensus Learning

2021-02-09 · Wenhao Li, Xiangfeng Wang, Bo Jin, Junjie Sheng 외

When solving a complex task, humans will spontaneously form teams and to complete different parts of the whole task, respectively. Meanwhile, the cooperation between teammates will improve efficiency. However, for curren…

Multi-agent Reinforcement Learning

Consensus Learning for Cooperative Multi-Agent Reinforcement Learning

2022-06-06 · Zhiwei Xu, Bin Zhang, Dapeng Li, Zeren Zhang 외

Almost all multi-agent reinforcement learning algorithms without communication follow the principle of centralized training with decentralized execution. During centralized training, agents can be guided by the same sign…

Contrastive LearningMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning+1