English

IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents

Machine Learning 2022-06-02 v1 Artificial Intelligence Computation and Language
Authors: Artem Zholus , Alexey Skrynnik , Shrestha Mohanty , Zoya Volovikova , Julia Kiseleva , Artur Szlam , Marc-Alexandre Coté , Aleksandr I. Panov
View on arXiv ↗ PDF ↗

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.

Keywords

embodied agent multi-agent systems

Cite

@article{arxiv.2206.00142,
  title  = {IGLU Gridworld: Simple and Fast Environment for Embodied Dialog Agents},
  author = {Artem Zholus and Alexey Skrynnik and Shrestha Mohanty and Zoya Volovikova and Julia Kiseleva and Artur Szlam and Marc-Alexandre Coté and Aleksandr I. Panov},
  journal= {arXiv preprint arXiv:2206.00142},
  year   = {2022}
}

Related papers

View all related →
Computation and Language · Computer Science
Interactive Grounded Language Understanding in a Collaborative Environment: IGLU 2021
Julia Kiseleva, Ziming Li, Mohammad Aliannejadi, Shrestha Mohanty +17
2022-05-30
Computation and Language · Computer Science
IGLU 2022: Interactive Grounded Language Understanding in a Collaborative Environment at NeurIPS 2022
Julia Kiseleva, Alexey Skrynnik, Artem Zholus, Shrestha Mohanty +13
2022-05-30
Artificial Intelligence · Computer Science
SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning
Haoqiang Kang, Xiaokang Ye, Yuhan Liu, Siddhant Hitesh Mantri +4
2026-05-14
Artificial Intelligence · Computer Science
Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual Environments
Zoya Volovikova, Alexey Skrynnik, Petr Kuderov, Aleksandr I. Panov
2024-07-15
Machine Learning · Computer Science
PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems
David Biagioni, Xiangyu Zhang, Dylan Wald, Deepthi Vaidhynathan +3
2021-11-12
Computation and Language · Computer Science
GLIDE-RL: Grounded Language Instruction through DEmonstration in RL
Chaitanya Kharyal, Sai Krishna Gottipati, Tanmay Kumar Sinha, Srijita Das +1
2024-01-09
Artificial Intelligence · Computer Science
A Survey on GUI Agents with Foundation Models Enhanced by Reinforcement Learning
Jiahao Li, Kaer Huang
2025-05-14
Artificial Intelligence · Computer Science
NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environment
Julia Kiseleva, Ziming Li, Mohammad Aliannejadi, Shrestha Mohanty +11
2021-10-18
Robotics · Computer Science
EmbodiedLGR: Integrating Lightweight Graph Representation and Retrieval for Semantic-Spatial Memory in Robotic Agents
Paolo Riva, Leonardo Gargani, Matteo Frosi, Matteo Matteucci
2026-04-21
Computation and Language · Computer Science
Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback
Nikhil Mehta, Milagro Teruel, Patricio Figueroa Sanz, Xin Deng +2
2024-02-07
Computation and Language · Computer Science
ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
Mohit Shridhar, Xingdi Yuan, Marc-Alexandre Côté, Yonatan Bisk +2
2021-03-16
Computation and Language · Computer Science
A Systematic Survey of Text Worlds as Embodied Natural Language Environments
Peter A Jansen
2021-07-12
Computation and Language · Computer Science
Grounded Language Learning in a Simulated 3D World
Karl Moritz Hermann, Felix Hill, Simon Green, Fumin Wang +10
2017-06-27
Computation and Language · Computer Science
LEGENT: Open Platform for Embodied Agents
Zhili Cheng, Zhitong Wang, Jinyi Hu, Shengding Hu +6
2024-08-20
Computation and Language · Computer Science
Embodied Task Planning via Graph-Informed Action Generation with Large Language Models
Xiang Li, Ning Yan, Masood Mortazavi
2026-05-19
Artificial Intelligence · Computer Science
Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents
Haonan Yu, Xiaochen Lian, Haichao Zhang, Wei Xu
2018-09-06
Artificial Intelligence · Computer Science
GriddlyJS: A Web IDE for Reinforcement Learning
Christopher Bamford, Minqi Jiang, Mikayel Samvelyan, Tim Rocktäschel
2022-10-14
Computation and Language · Computer Science
Grid Spatial Understanding: A Dataset for Textual Spatial Reasoning over Grids, Embodied Settings, and Coordinate Structures
Risham Sidhu, Julia Hockenmaier
2026-03-19
Machine Learning · Computer Science
Language-Conditioned Goal Generation: a New Approach to Language Grounding for RL
Cédric Colas, Ahmed Akakzia, Pierre-Yves Oudeyer, Mohamed Chetouani +1
2020-06-15
Computation and Language · Computer Science
SILG: The Multi-environment Symbolic Interactive Language Grounding Benchmark
Victor Zhong, Austin W. Hanjie, Sida I. Wang, Karthik Narasimhan +1
2022-01-26
Artificial Intelligence · Computer Science
Imagined Autocurricula
Ahmet H. Güzel, Matthew Thomas Jackson, Jarek Luca Liesen, Tim Rocktäschel +3
2025-09-30
Machine Learning · Computer Science
APES: a Python toolbox for simulating reinforcement learning environments
Aqeel Labash, Ardi Tampuu, Tambet Matiisen, Jaan Aru +1
2018-09-03
Artificial Intelligence · Computer Science
AgentFly: Extensible and Scalable Reinforcement Learning for LM Agents
Renxi Wang, Rifo Ahmad Genadi, Bilal El Bouardi, Yongxin Wang +4
2025-07-22
Computation and Language · Computer Science
Interactive Grounded Language Acquisition and Generalization in a 2D World
Haonan Yu, Haichao Zhang, Wei Xu
2018-08-15
Machine Learning · Computer Science
Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning
Hugo Caselles-Dupré, Louis Annabi, Oksana Hagen, Michael Garcia-Ortiz +1
2018-09-11
R2 v1 2026-06-24T11:35:15.232Z