Dear all / Bonjour à tous,

We are happy to invite you to Abhinav Gupta's PhD defense on November 19th, at 9 am (remote).

Vous êtes cordialement invité.e.s à la soutenance de thèse d'Abhinav Gupta, le 19 novembre à 9 am (à distance).

Jury

Abstract

Multi-agent systems provide a framework to play with a population of agents
to simulate human-like behavior in artificial environments. They allow us
to train artificial agents using self-play so that they can develop
strategies to solve problems while collaborating/competing with other
agents in an environment. Multi-agent communication imitates this setup
where agents are trained to develop emergent languages that are then used
to solve cooperative (or mixed) tasks. The eventual goal is to bridge the
gap between these emergent languages and natural language for efficient
communication with humans. This work aims to augment artificial agents with
the capability to use and understand natural language. To this end, I
present three articles that explore different facets of this research
problem. I investigate and provide algorithms that show how populations and
self-play can help in learning diverse strategies that can facilitate
human-agent communication.