Deep Multi-Agent Reinforcement Learning with Relevance Graphs

2018/11/30 by Aleksandra Malysheva, Malysheva, Aleksandra, Tegg Tae Kyong Sung +7 · 2 citations
Computer Science · Engineering · #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multiagent Systems (cs.MA) #Reinforcement Learning in Robotics #Robot Manipulation and Learning

paper · pdf · doi:10.48550/arxiv.1811.12557

openalex publication_date 2018/11/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Over recent years, deep reinforcement learning has shown strong successes in complex single-agent tasks, and more recently this approach has also been applied to multi-agent domains. In this paper, we propose a novel approach, called MAGnet, to multi-agent reinforcement learning (MARL) that utilizes a relevance graph representation of the environment obtained by a self-attention mechanism, and a message-generation technique inspired by the NerveNet architecture. We applied our MAGnet approach to the Pommerman game and the results show that it significantly outperforms state-of-the-art MARL solutions, including DQN, MADDPG, and MCTS.

Citations

• Playing Atari with Deep Reinforcement Learning
• Continuous control with deep reinforcement learning
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
• Learning to Search with MCTSnets

Cited by

• Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities
• HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning

Related

• Multi-Agent Deep Reinforcement Learning using Attentive Graph Neural Architectures for Real-Time Strategy Games
• Reinforcement Networks: novel framework for collaborative Multi-Agent Reinforcement Learning tasks
• Multi-agent Reinforcement Learning: A Comprehensive Survey
• Decentralized Graph-Based Multi-Agent Reinforcement Learning Using Reward Machines
• HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messaging