Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols
Serhii Havrylov, Ivan Titov
Feb 17, 2017 (modified: Mar 20, 2017)ICLR 2017 workshop submissionreaders: everyone
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.
Keywords:Natural language processing, Deep learning, Multi-modal learning, Games
Enter your feedback below and we'll get back to you as soon as possible.