2024-01-23-villanger24a.md

title	openreview	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
An Inductive Bias for Emergent Communication in a Continuous Setting	TdieTXeza3	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.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	villanger24a	0	An Inductive Bias for Emergent Communication in a Continuous Setting	235	243	235-243	235	false	Villanger, John Isak Fjellvang and Bojesen, Troels Arnfred	given family John Isak Fjellvang Villanger given family Troels Arnfred Bojesen	2024-01-23		Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL})	233	inproceedings	date-parts 2024 1 23	https://proceedings.mlr.press/v233/villanger24a/villanger24a.pdf