We introduce The House Of inteRactions (THOR), a framework for visual AI research, available at ai2thor.allenai.org. AI2-THOR consists of near photo-realistic 3D indoor scenes, where AI agents can navigate in the scenes and interact with objects to perform tasks.

AI2-THOR enables research in many different domains including but not limited to deep reinforcement learning, imitation learning, learning by interaction, planning, visual question answering, unsupervised representation learning, object detection and segmentation, and learning models of cognition. The goal of AI2-THOR is to facilitate building visually intelligent models and push the research forward in this domain.

Cite this

@article{ai2thor, title={{AI2-THOR: An Interactive 3D Environment for Visual AI}}, author={Kolve, Eric and Mottaghi, Roozbeh and Gordon, Daniel and Han, Winson and VanderBilt, Eli and Weihs, Luca and Herrasti, Alvaro and Deitke, Matt and Ehsani, Kiana and Zhu, Yuke and Gupta, Abhinav and Farhadi, Ali}, journal={arXiv preprint arXiv:1712.05474}, year={2017} }