Skip to Content
Reinforcement Learning with TensorFlow
book

Reinforcement Learning with TensorFlow

by Sayon Dutta
April 2018
Intermediate to advanced content levelIntermediate to advanced
334 pages
10h 18m
English
Packt Publishing
Content preview from Reinforcement Learning with TensorFlow

Actions

There are two categories of possible actions as follows:

  • Movement actions implying a change in the current observed region
  • Terminal action to indicate that the object is detected and that the search has ended

Each movement action can only transfer the attention top-down between regions from a predefined hierarchy. The image gets further segregated into five smaller sub-regions to focus upon. Hence, a hierarchy is built in the five sub-regions (in the following figure) created as:

  • Four quarters
  • One central overlapping region

Thus, there are five movement actions, each associated with sub-regions and one terminal action, which is ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

Deep Learning with TensorFlow - Second Edition

Deep Learning with TensorFlow - Second Edition

Giancarlo Zaccone, Vihan Jain, Md. Rezaul Karim, Motaz Saad
Deep Learning with TensorFlow 2 and Keras - Second Edition

Deep Learning with TensorFlow 2 and Keras - Second Edition

Antonio Gulli, Dr. Amita Kapoor, Sujit Pal

Publisher Resources

ISBN: 9781788835725Supplemental Content