Publication
Title
Scalability of message encoding techniques for continuous communication learned with multi-agent reinforcement learning
Author
Abstract
Many multi-agent systems require inter-agent communication to properly achieve their goal. By learning the communication protocol alongside the action protocol using multi-agent reinforcement learning techniques, the agents gain the flexibility to determine which information should be shared. However, when the number of agents increases we need to create an encoding of the information contained in these messages. In this paper, we investigate the effect of increasing the amount of information that should be contained in a message and increasing the number of agents. We evaluate these effects on two different message encoding methods, the mean message encoder and the attention message encoder. We perform our experiments on a matrix environment. Surprisingly, our results show that the mean message encoder consistently outperforms the attention message encoder. Therefore, we analyse the communication protocol used by the agents that use the mean message encoder and can conclude that the agents use a combination of an exponential and a logarithmic function in their communication policy to avoid the loss of important information after applying the mean message encoder.
Language
English
Source (book)
34th Benelux Conference on Artificial Intelligence and the 31 Belgium Dutch Conference on Machine Learning (BNAIC/BENELEARN 2022), 7-9 November, 2022, Mechelen, Belgium
Publication
2022
Volume/pages
p. 1-16
Medium
E-only publicatie
Full text (open access)
UAntwerpen
Faculty/Department
Research group
Project info
Learning to communicate efficiently with multi-agent reinforcement learning for distributed control applications.
Multi-Agent Communication and Behaviour Training using Reinforcement Learning.
Publication type
Subject
Affiliation
Publications with a UAntwerp address
External links
Source file
Record
Identifier
Creation 12.12.2023
Last edited 17.06.2024
To cite this reference