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

TL;DR

This paper introduces HC-MARL, a hierarchical consensus-based framework for multi-agent reinforcement learning that improves cooperation in multi-robot tasks by forming global consensus from local observations without direct communication.

Contribution

The paper proposes a novel hierarchical consensus mechanism using contrastive learning and adaptive attention to enhance multi-agent cooperation in MARL, addressing the global guidance gap.

Findings

HC-MARL outperforms baseline methods in multi-robot tasks.

The hierarchical consensus improves cooperation without communication.

Adaptive attention optimizes consensus influence dynamically.

Abstract

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.