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.

cs.LG cs.AI cs.CL Multimodal Machine Learning Applications Multi-Agent Systems and Negotiation Reinforcement Learning in Robotics

Paper

Similar papers

Interactive Grounded Language Understanding in a Collaborative Environment: IGLU 2021Julia Kiseleva, Ziming Li, Mohammad Aliannejadi et al.2022 · UvA-DARE (University of Amsterdam) · 37 citations In Library

GriddlyJS: A Web IDE for Reinforcement LearningC. Bamford, Minqi Jiang, Mikayel Samvelyan et al.2022 · Neural Information Processing Systems · 6 citations In Library

Interactive Grounded Language Acquisition and Generalization in a 2D WorldHaonan Yu, Haichao Zhang, W. Xu2018 · International Conference on Learning Representations · 80 citations In Library

GridToPix: Training Embodied Agents with Minimal SupervisionUnnat Jain, Iou-Jen Liu, Svetlana Lazebnik et al.2021 · arXiv (Cornell University) · 25 citations In Library

GridToPix: Training Embodied Agents with Minimal SupervisionUnnat Jain, Iou-Jen Liu, Svetlana Lazebnik et al.2021 · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) In Library

SocialGrid: A Benchmark for Planning and Social Reasoning in Embodied Multi-Agent SystemsHikaru Shindo, Hanzhao Lin, Lukas Helff et al.2026 · 0 citations In Library

Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World SuccessGeorge Bredis, Stanislav Dereka, Viacheslav Sinii et al.2026 In Library

Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World SuccessGeorge Bredis, Stanislav Dereka, Viacheslav Sinii et al.2025 · Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems · 5 citations In Library

Gridworld Testbed for Intelligent Agent ArchitectureAhmed M. Kareem, Ali Obied2021 In Library

GLIDE-RL: Grounded Language Instruction through DEmonstration in RLChaitanya Kharyal, Sai Krishna Gottipati, Tanmay Kumar Sinha et al.2024 · arXiv (Cornell University) In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal