Interactive Grounded Language Understanding in a Collaborative Environment: IGLU 2021

TL;DR

IGLU 2021 is a competition focused on developing interactive agents capable of understanding and executing grounded natural language instructions within a collaborative environment, aiming to advance research in adaptive language understanding.

Contribution

The paper introduces IGLU, a new benchmark and competition framework designed to evaluate interactive grounded language understanding in collaborative settings.

Findings

Multiple approaches demonstrated improved task learning from natural language instructions.

Participants developed agents capable of adapting to new tasks through grounded language understanding.

The competition highlighted key challenges and progress in interactive language learning.

Abstract

Human intelligence has the remarkable ability to quickly adapt to new tasks and environments. Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by imitating the behavior of others or by following provided natural language instructions. To facilitate research in this direction, we propose \emph{IGLU: Interactive Grounded Language Understanding in a Collaborative Environment}. The primary goal of the competition is to approach the problem of how to build interactive agents that learn to solve a task while provided with grounded natural language instructions in a collaborative environment. Understanding the complexity of the challenge, we split it into sub-tasks to make it feasible for participants.