DeepAI AI Chat
Log In Sign Up

Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence

by   Emilio Jorge, et al.
Chalmers University of Technology

Acquiring your first language is an incredible feat and not easily duplicated. Learning to communicate using nothing but a few pictureless books, a corpus, would likely be impossible even for humans. Nevertheless, this is the dominating approach in most natural language processing today. As an alternative, we propose the use of situated interactions between agents as a driving force for communication, and the framework of Deep Recurrent Q-Networks for evolving a shared language grounded in the provided environment. We task the agents with interactive image search in the form of the game Guess Who?. The images from the game provide a non trivial environment for the agents to discuss and a natural grounding for the concepts they decide to encode in their communication. Our experiments show that the agents learn not only to encode physical concepts in their words, i.e. grounding, but also that the agents learn to hold a multi-step dialogue remembering the state of the dialogue from step to step.


page 1

page 2

page 3

page 4


Talk the Walk: Navigating New York City through Grounded Dialogue

We introduce "Talk The Walk", the first large-scale dialogue dataset gro...

Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent

Contrary to most natural language processing research, which makes use o...

How Should Agents Ask Questions For Situated Learning? An Annotated Dialogue Corpus

Intelligent agents that are confronted with novel concepts in situated e...

Learning to Speak and Act in a Fantasy Text Adventure Game

We introduce a large scale crowdsourced text adventure game as a researc...

Emergent Communication with Attention

To develop computational agents that better communicate using their own ...

gComm: An environment for investigating generalization in Grounded Language Acquisition

gComm is a step towards developing a robust platform to foster research ...

Reference-Centric Models for Grounded Collaborative Dialogue

We present a grounded neural dialogue model that successfully collaborat...