Picture for Artur Szlam

Artur Szlam

IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents

Add code
May 31, 2022
Artem Zholus, Alexey Skrynnik, Shrestha Mohanty, Zoya Volovikova, Julia Kiseleva, Artur Szlam, Marc-Alexandre Coté, Aleksandr I. Panov
Figure 1 for IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents
Figure 2 for IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents
Figure 3 for IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents

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.

Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon