Graph Based Deep Reinforcement Learning Aided by Transformers for Multi-Agent Cooperation

2025-04-11 · Michael Elrod, Niloufar Mehrabi, Rahul Amin, Manveen Kaur, Long Cheng, Jim Martin, Abolfazl Razi

Mission planning for a fleet of cooperative autonomous drones in applications that involve serving distributed target points, such as disaster response, environmental monitoring, and surveillance, is challenging, especially under partial observability, limited communication range, and uncertain environments. Traditional path-planning algorithms struggle in these scenarios, particularly when prior information is not available. To address these challenges, we propose a novel framework that integrates Graph Neural Networks (GNNs), Deep Reinforcement Learning (DRL), and transformer-based mechanisms for enhanced multi-agent coordination and collective task execution. Our approach leverages GNNs to model agent-agent and agent-goal interactions through adaptive graph construction, enabling efficient information aggregation and decision-making under constrained communication. A transformer-based message-passing mechanism, augmented with edge-feature-enhanced attention, captures complex interaction patterns, while a Double Deep Q-Network (Double DQN) with prioritized experience replay optimizes agent policies in partially observable environments. This integration is carefully designed to address specific requirements of multi-agent navigation, such as scalability, adaptability, and efficient task execution. Experimental results demonstrate superior performance, with 90% service provisioning and 100% grid coverage (node discovery), while reducing the average steps per episode to 200, compared to 600 for benchmark methods such as particle swarm optimization (PSO), greedy algorithms and DQN.

📄 PDF Abstract BibTeX arXiv:2504.08195

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningDisaster Responsegraph construction

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…

Prioritized Experience Replay Prioritized Experience Replay is a type of experience replay in reinforcement learning where we more frequently replay…

DQN A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari…

Search-Aided Joint Agent-Environment Reinforcement Learning for Robust Lifelong Multi-Agent Path Finding with Rotations

2026-08-06 · He Jiang, Jingtian Yan, Yulun Zhang, Yimin Tang 외 arxiv

Lifelong Multi-Agent Path Finding (LMAPF) requires repeatedly planning collision-free paths for agents that continuously receive new goals upon reaching their current ones. While many learning-based planners have been pr…

Reinforcement Learning

Sub-optimal Policy Aided Multi-Agent Reinforcement Learning for Flocking Control

2022-09-17 · Yunbo Qiu, Yue Jin, Jian Wang, Xudong Zhang

Flocking control is a challenging problem, where multiple agents, such as drones or vehicles, need to reach a target position while maintaining the flock and avoiding collisions with obstacles and collisions among agents…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems

2023-01-13 · Matteo Gallici, Mario Martin, Ivan Masmitja

Coordination is one of the most difficult aspects of multi-agent reinforcement learning (MARL). One reason is that agents normally choose their actions independently of one another. In order to see coordination strategie…

Multi-agent Reinforcement Learning Q-Learning Starcraft Starcraft II+1

Model-aided Federated Reinforcement Learning for Multi-UAV Trajectory Planning in IoT Networks

2023-06-03 · Jichao Chen, Omid Esrafilian, Harald Bayerlein, David Gesbert 외

Deploying teams of unmanned aerial vehicles (UAVs) to harvest data from distributed Internet of Things (IoT) devices requires efficient trajectory planning and coordination algorithms. Multi-agent reinforcement learning …

Federated Learning Multi-agent Reinforcement Learning Trajectory Planning

An Overview of Machine Learning-Enabled Optimization for Reconfigurable Intelligent Surfaces-Aided 6G Networks: From Reinforcement Learning to Large Language Models

2024-05-09 · Hao Zhou, Chengming Hu, Xue Liu

Reconfigurable intelligent surface (RIS) becomes a promising technique for 6G networks by reshaping signal propagation in smart radio environments. However, it also leads to significant complexity for network management …

Hierarchical Reinforcement Learning Management Multi-agent Reinforcement Learning Q-Learning+4