Source
CVPR
DATE OF PUBLICATION
05/27/2022
Authors
Alexander Panov Konstantin Yakovlev Artem Zholus Shrestha Mohanty Artur Szlam Marc-Alexandre Cote Zoya Volovikova Julia Kiseleva
Share

IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents

Abstract

We present the IGLU Gridworld: a reinforcement learning environment for building and evaluating language conditioned embodied agents in a scalable way. The environment features visual agent embodiment, interactive learning through collaboration, language conditioned RL, and combinatorically hard task (3d blocks building) space.

Join AIRI on social media