QMNet: Importance-Aware Message Exchange for Decentralized Multi-Agent Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
To improve the performance of multi-agent reinforcement learning under the constraint of wireless resources, we propose a message importance metric and design an importance-aware scheduling policy to effectively exchange messages. The key insight is spending the precious communication resources on important messages. The message importance depends not only on the messages themselves, but also on the needs of agents who receive them. Accordingly, we propose a query-message-based architecture, called QMNet. Agents generate queries and messages with the environment observation. Sharing queries can help calculate message importance. Exchanging messages can help agents cooperate better. Besides, we exploit the message importance to deal with random access collisions in decentralized systems. Furthermore, a message prediction mechanism is proposed to compensate for messages that are not transmitted. Finally, we evaluate the proposed schemes in a traffic junction environment, where only a fraction of agents can send messages due to limited wireless resources. Results show that QMNet can extract valuable information to guarantee the system performance even when only 30% of agents can share messages. By exploiting message prediction, the system can further save 40% of wireless resources. The importance-aware decentralized multi-access mechanism can effectively avoid collisions, achieving almost the same performance as centralized scheduling.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 39 references that are in the map. First posted on arXiv 18 Jul 2023.
Builds on
24 of 39 references.
References · 24
- 2015Continuous control with deep reinforcement learningcited by 3,407
- 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
- 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
- 2017Counterfactual Multi-Agent Policy Gradientscited by 751
- 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 708
- 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 575
- 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 379
- 2016Learning Multiagent Communication with Backpropagationcited by 366
- 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 268
- 2018Actor-Attention-Critic for Multi-Agent Reinforcement Learningcited by 261
- 2018TarMAC: Targeted Multi-Agent Communicationcited by 208
- 2018Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agentscited by 194
12 more
- 2018Learning Attentional Communication for Multi-Agent Cooperationcited by 175
- 2018Graph Convolutional Reinforcement Learningcited by 152
- 2018Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Taskscited by 121
- 2017Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Gamescited by 96
- 2017A Survey of Learning in Multiagent Environments: Dealing with Non-Stationaritycited by 94
- 2019Learning to Schedule Communication in Multi-agent Reinforcement Learningcited by 93
- 2020Learning Individually Inferred Communication for Multi-Agent Cooperationcited by 55
- 2017VAIN: Attentional Multi-agent Predictive Modelingcited by 53
- 2021Attention-based Reinforcement Learning for Real-Time UAV Semantic Communicationcited by 14
- 2021HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messagingcited by 13
- 2020Counterfactual Multi-Agent Reinforcement Learning with Graph Convolution Communicationcited by 12
- 2021Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learningcited by 11
Built on by
Not cited yet.