IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents

2022/05/31 by Zholus, Artem, Skrynnik, Alexey, Mohanty, Shrestha +5
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2206.00142

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.

Related

• IGLU 2022: Interactive Grounded Language Understanding in a Collaborative Environment at NeurIPS 2022
• NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environment
• Scaling Instructable Agents Across Many Simulated Worlds
• Large Language Models as Generalizable Policies for Embodied Tasks
• ALFWorld: Aligning Text and Embodied Environments for Interactive Learning