Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols

Serhii Havrylov, Ivan Titov

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.

TL;DR: We proposed an efficient learning strategy for developing communication protocol(variable-length sequences of discrete symbols) between two agents for playing a referential game.

Conflicts: uva.nl

Keywords: Natural language processing, Deep learning, Multi-modal learning, Games