30 April: Serhii Havrylov

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

Serhii Havrylov (Institute for Language, Cognition and Computation, University of Edinburgh)

Tuesday, April 30
11:00am – 12:30pm
Room 1.17, DSB

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. Unlike previous work, we require that messages they exchange, both at train and test time, are in the form of sequences of discrete symbols. We compare a reinforcement learning approach and one using a differentiable relaxation. We also observe that the protocol we induce by optimising the communication success exhibits a degree of compositionality and variability (i.e. the same information can be phrased in different ways), both properties characteristic of natural languages. As the ultimate goal is to ensure that communication is accomplished in natural language, we also perform experiments where we inject prior information about natural language into our model and study properties of the resulting protocol.