Multi-agent Communication with Graph Information Bottleneck under Limited Bandwidth

12/20/2021
by   Qi Tian, et al.
0

Recent studies have shown that introducing communication between agents can significantly improve overall performance in cooperative Multi-agent reinforcement learning (MARL). In many real-world scenarios, communication can be expensive and the bandwidth of the multi-agent system is subject to certain constraints. Redundant messages who occupy the communication resources can block the transmission of informative messages and thus jeopardize the performance. In this paper, we aim to learn the minimal sufficient communication messages. First, we initiate the communication between agents by a complete graph. Then we introduce the graph information bottleneck (GIB) principle into this complete graph and derive the optimization over graph structures. Based on the optimization, a novel multi-agent communication module, called CommGIB, is proposed, which effectively compresses the structure information and node information in the communication graph to deal with bandwidth-constrained settings. Extensive experiments in Traffic Control and StanCraft II are conducted. The results indicate that the proposed methods can achieve better performance in bandwidth-restricted settings compared with state-of-the-art algorithms, with especially large margins in large-scale multi-agent tasks.

READ FULL TEXT
research
11/16/2019

Learning Efficient Multi-agent Communication: An Information Bottleneck Approach

Many real-world multi-agent reinforcement learning applications require ...
research
10/27/2020

Succinct and Robust Multi-Agent Communication With Temporal Message Control

Recent studies have shown that introducing communication between agents ...
research
07/30/2023

Efficient Q-Learning over Visit Frequency Maps for Multi-agent Exploration of Unknown Environments

The robot exploration task has been widely studied with applications spa...
research
09/06/2019

Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control

Multi-agent reinforcement learning (MARL) has recently received consider...
research
01/05/2021

Neurosymbolic Transformers for Multi-Agent Communication

We study the problem of inferring communication structures that can solv...
research
06/16/2023

Dynamic Size Message Scheduling for Multi-Agent Communication under Limited Bandwidth

Communication plays a vital role in multi-agent systems, fostering colla...
research
02/26/2019

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

Communication is an important factor for the big multi-agent world to st...

Please sign up or login with your details

Forgot password? Click here to reset