Published on Tue Feb 26 2019

Learning Multi-agent Communication under Limited-bandwidth Restriction for Internet Packet Routing

Hangyu Mao, Zhibo Gong, Zhengchao Zhang, Zhen Xiao, Yan Ni

Communication is an important factor for the big multi-agent world. Most previous methods keep sending messages incessantly in every control cycle. These methods are unsuitable to be applied to the real-world systems. To adaptively prune unprofitable messages, we propose a gating mechanism.

0
0
0
Abstract

Communication is an important factor for the big multi-agent world to stay organized and productive. Recently, the AI community has applied the Deep Reinforcement Learning (DRL) to learn the communication strategy and the control policy for multiple agents. However, when implementing the communication for real-world multi-agent applications, there is a more practical limited-bandwidth restriction, which has been largely ignored by the existing DRL-based methods. Specifically, agents trained by most previous methods keep sending messages incessantly in every control cycle; due to emitting too many messages, these methods are unsuitable to be applied to the real-world systems that have a limited bandwidth to transmit the messages. To handle this problem, we propose a gating mechanism to adaptively prune unprofitable messages. Results show that the gating mechanism can prune more than 80% messages with little damage to the performance. Moreover, our method outperforms several state-of-the-art DRL-based and rule-based methods by a large margin in both the real-world packet routing tasks and four benchmark tasks.

Tue Dec 03 2019
Artificial Intelligence
Learning Agent Communication under Limited Bandwidth by Message Pruning
Communication is a crucial factor for the big multi-agent world to stay organized and productive. Many methods keep sending messages incessantly, which consumes too much bandwidth. To handle this problem, we propose a gating mechanism to adaptively prune less beneficial messages.
0
0
0
Thu May 09 2019
Artificial Intelligence
Toward Packet Routing with Fully-distributed Multi-agent Deep Reinforcement Learning
Packet routing is one of the fundamental problems in computer networks. In this paper, we propose a novel routing framework based on deep reinforcement learning. The LSTM recurrent neural network extracts routing features from rich information regarding backlogged packets and past actions.
0
0
0
Mon Mar 29 2021
Machine Learning
Deep reinforcement learning of event-triggered communication and control for multi-agent cooperative transport
0
0
0
Thu Dec 31 2020
Artificial Intelligence
Relational Deep Reinforcement Learning for Routing in Wireless Networks
Routing in wireless networks has been studied extensively, but existing protocols are typically designed for a specific set of network conditions. In this paper, we develop a distributed routing strategy that generalizes to diverse traffic patterns, congestion levels, network connectivity, and link dynamics.
0
0
0
Tue Feb 11 2020
Machine Learning
Learning Structured Communication for Multi-agent Reinforcement Learning
This work explores the large-scale multi-agent communication mechanism under a multi- agent reinforcement learning (MARL) setting. We propose a novel framework termed as Learning Structured Communication (LSC) by using a more flexible and efficient communication topology.
0
0
0
Wed Jul 28 2021
Artificial Intelligence
Packet Routing with Graph Attention Multi-agent Reinforcement Learning
Packet routing is a fundamental problem in communication networks. With the increasing complexity of network topology, conventional routing schemes show significant limitations. Adding intelligence to the network control is becoming a trend and the key to achieving high-efficiency network operation.
1
0
0