Neural Information Processing Systems http://nips.cc/

As a motivating example, consider deploying a robot agent at scale in a varietyofhomeenvironments. Therobotshouldgeneralize byperforming robustlynotonlyintest homes, butinanyenduser'shome.

These imaging systems fail to capture dynamic objects. Recently, snapshotcompressiveimaging (SCI)systems [17,18,19]have been developed to capture HSIs at video rate.

Due to the non-convex nature of such joint estimators, the theoretical justification of their efficiency is typically challenging.

The solution in [5,4]requires aone-pass forward computation of marginal probabilities.

A.1 List of objects, containers, surfaces, and rooms in the apartment We list all the objects that are included in our experimental environment. We use the object rearrangement tasks for evaluation. The tasks are randomly sampled from different distributions. Simple: this task is to move one object in the house to the desired location. Novel Simple: this task is to move one object in the house to the desired location.

Neural Information Processing Systems http://nips.cc/