English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose a method for sim-to-real robot learning which exploits simulatorstate information in a way that scales to many objects. We first train a pairof encoder networks to capture multi-object state information in a latentspace. One of these encoders is a CNN, which enables our system to operate onRGB images in the real world; the other is a graph neural network (GNN) stateencoder, which directly consumes a set of raw object poses and enables moreaccurate reward calculation and value estimation. Once trained, we use theseencoders in a reinforcement learning algorithm to train image-based policiesthat can manipulate many objects. We evaluate our method on the task of pushinga collection of objects to desired tabletop regions. Compared to methods whichrely only on images or use fixed-length state encodings, our method achieveshigher success rates, performs well in the real world without fine tuning, andgeneralizes to different numbers and types of objects not seen during training.

Learning to Manipulate Object Collections Using Grounded State Representations