IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents

2022-05-31Code Available1· sign in to hype

Artem Zholus, Alexey Skrynnik, Shrestha Mohanty, Zoya Volovikova, Julia Kiseleva, Artur Szlam, Marc-Alexandre Coté, Aleksandr I. Panov

arXiv PDF

Code Available — Be the first to reproduce this paper.

Reproduce

Code

github.com/iglu-contest/gridworld
OfficialIn papernone★ 36

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.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents

Code

Abstract

Tasks

Reproductions