Emergence of Language with Multi-Agent Games: Learning to Communicate with Sequence of Symbols

Serhii Havrylov, Ivan Titov

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Learning to communicate through interaction, rather than relying on explicit supervision, is often considered a prerequisite for developing a general AI. We study a setting where two agents engage in playing a referential game and, from scratch, develop a communication protocol necessary to succeed in this game. We require that messages they exchange, both at train and test time, are in the form of a language (i.e. sequences of discrete symbols). As the ultimate goal is to ensure that communication is accomplished in natural language, we perform preliminary experiments where we inject prior information about natural language into our model and study properties of the resulting protocol.
Original languageEnglish
Title of host publication5th International Conference on Learning Representations (ICLR 17, workshop track)
Number of pages6
Publication statusE-pub ahead of print - 26 Apr 2017
Event5th International Conference on Learning Representations - Palais des Congrès Neptune, Toulon, France
Duration: 24 Apr 201726 Apr 2017
https://iclr.cc/archive/www/2017.html

Conference

Conference5th International Conference on Learning Representations
Abbreviated titleICLR 2017
CountryFrance
CityToulon
Period24/04/1726/04/17
Internet address

Fingerprint Dive into the research topics of 'Emergence of Language with Multi-Agent Games: Learning to Communicate with Sequence of Symbols'. Together they form a unique fingerprint.

Cite this