Saved in:
Bibliographic Details
Main Authors: Chen, Hang, Jang, Yuchuan, Zhou, Weijie, Meo, Cristian, Chen, Ziwei, Liu, Dianbo
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.15985
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909353674539008
author Chen, Hang
Jang, Yuchuan
Zhou, Weijie
Meo, Cristian
Chen, Ziwei
Liu, Dianbo
author_facet Chen, Hang
Jang, Yuchuan
Zhou, Weijie
Meo, Cristian
Chen, Ziwei
Liu, Dianbo
contents Individuals, despite having varied life experiences and learning processes, can communicate effectively through languages. This study aims to explore the efficiency of language as a communication medium. We put forth two specific hypotheses: First, discrete messages are more effective than continuous ones when agents have diverse personal experiences. Second, communications using multiple discrete tokens are more advantageous than those using a single token. To valdate these hypotheses, we designed multi-agent machine learning experiments to assess communication efficiency using various information transmission methods between speakers and listeners. Our empirical findings indicate that, in scenarios where agents are exposed to different data, communicating through sentences composed of discrete tokens offers the best inter-agent communication efficiency. The limitations of our finding include lack of systematic advantages over other more sophisticated encoder-decoder model such as variational autoencoder and lack of evluation on non-image dataset, which we will leave for future studies.
format Preprint
id arxiv_https___arxiv_org_abs_2312_15985
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Discrete Messages Improve Communication Efficiency among Isolated Intelligent Agents
Chen, Hang
Jang, Yuchuan
Zhou, Weijie
Meo, Cristian
Chen, Ziwei
Liu, Dianbo
Machine Learning
Information Theory
Individuals, despite having varied life experiences and learning processes, can communicate effectively through languages. This study aims to explore the efficiency of language as a communication medium. We put forth two specific hypotheses: First, discrete messages are more effective than continuous ones when agents have diverse personal experiences. Second, communications using multiple discrete tokens are more advantageous than those using a single token. To valdate these hypotheses, we designed multi-agent machine learning experiments to assess communication efficiency using various information transmission methods between speakers and listeners. Our empirical findings indicate that, in scenarios where agents are exposed to different data, communicating through sentences composed of discrete tokens offers the best inter-agent communication efficiency. The limitations of our finding include lack of systematic advantages over other more sophisticated encoder-decoder model such as variational autoencoder and lack of evluation on non-image dataset, which we will leave for future studies.
title Discrete Messages Improve Communication Efficiency among Isolated Intelligent Agents
topic Machine Learning
Information Theory
url https://arxiv.org/abs/2312.15985