Event-triggered Multi-agent Reinforcement Learning With Communication Under Limited-bandwidth Constraint

Abstract

Communicating with each other in a distributed manner and behaving as a group are essential in multi-agent reinforcement learning. However, real-world multi-agent systems suffer from restrictions on limited-bandwidth communication. If the bandwidth is fully occupied, some agents are not able to send messages promptly to others, causing decision delay and impairing cooperative effects. Recent related work has started to address the problem but still fails in maximally reducing the consumption of communication resources. In this paper, we propose Event-Triggered Communication Network (ETCNet) to enhance the communication efficiency in multi-agent systems by sending messages only when necessary. According to the information theory, the limited bandwidth is translated to the penalty threshold of an event-triggered strategy, which determines whether an agent at each step sends a message or not. Then the design of the event-triggered strategy is formulated as a constrained Markov decision pr

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhu2020event

Related papers

• Learning To Schedule Communication In Multi-agent Reinforcement Learning (2019)0.00
• Event-based Communication In Distributed Q-learning (2021)2.26
• Minimizing Communication While Maximizing Performance In Multi-agent Reinforcement Learning (2021)0.00
• Multi-agent Reinforcement Learning With Communication-constrained Priors (2025)0.00
• Learning Practical Communication Strategies In Cooperative Multi-agent Reinforcement Learning (2022)0.00
• Low-bandwidth Communication Emerges Naturally In Multi-agent Learning Systems (2020)0.00
• Context-aware Communication For Multi-agent Reinforcement Learning (2023)3.14
• Provably Efficient Multi-agent Reinforcement Learning With Fully Decentralized Communication (2021)0.00