Источник
CVPR
Дата публикации
27.05.2022
Авторы
Александр Панов Алексей Скрынник Артем Жолус Shrestha Mohanty Artur Szlam Marc-Alexandre Cote Зоя Воловикова Юлия Киселева
Поделиться

IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents

Аннотация

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.

Присоединяйтесь к AIRI в соцсетях