Representation Learning for Grounded Spatial Reasoning

Representation Learning for Grounded Spatial Reasoning

<jats:p>The interpretation of spatial references is highly contextual, requiring joint inference over both language and the environment. We consider the task of spatial reasoning in a simulated environment, where an agent can act and receive rewards. The proposed model learns a representation...

Full description

Bibliographic Details
Main Authors: Janner, Michael, Narasimhan, Karthik, Barzilay, Regina
Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Format: Article
Language:English
Published: MIT Press - Journals 2021
Online Access:https://hdl.handle.net/1721.1/135064

Internet

https://hdl.handle.net/1721.1/135064

Similar Items