Inductive Bias for Emergent Communication in a Continuous Setting

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Villanger, John Isak Fjellvang, Bojesen, Troels Arnfred
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929561465257984
author Villanger, John Isak Fjellvang
Bojesen, Troels Arnfred
author_facet Villanger, John Isak Fjellvang
Bojesen, Troels Arnfred
contents We study emergent communication in a multi-agent reinforcement learning setting, where the agents solve cooperative tasks and have access to a communication channel. The communication channel may consist of either discrete symbols or continuous variables. We introduce an inductive bias to aid with the emergence of good communication protocols for continuous messages, and we look at the effect this type of inductive bias has for continuous and discrete messages in itself or when used in combination with reinforcement learning. We demonstrate that this type of inductive bias has a beneficial effect on the communication protocols learnt in two toy environments, Negotiation and Sequence Guess.
format Preprint
id arxiv_https___arxiv_org_abs_2306_03830
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Inductive Bias for Emergent Communication in a Continuous Setting
Villanger, John Isak Fjellvang
Bojesen, Troels Arnfred
Machine Learning
Artificial Intelligence
Multiagent Systems
I.2.11
We study emergent communication in a multi-agent reinforcement learning setting, where the agents solve cooperative tasks and have access to a communication channel. The communication channel may consist of either discrete symbols or continuous variables. We introduce an inductive bias to aid with the emergence of good communication protocols for continuous messages, and we look at the effect this type of inductive bias has for continuous and discrete messages in itself or when used in combination with reinforcement learning. We demonstrate that this type of inductive bias has a beneficial effect on the communication protocols learnt in two toy environments, Negotiation and Sequence Guess.
title Inductive Bias for Emergent Communication in a Continuous Setting
topic Machine Learning
Artificial Intelligence
Multiagent Systems
I.2.11
url https://arxiv.org/abs/2306.03830