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

Recurrent temporal aggregation

Recurrent temporal aggregation involves aggregating environmental states across different time steps. Let's discuss the reason behind this in detail. First, fetching environmental states is not an easy task and sensor readings provide the best possible state representation of the environment. Therefore, state information of the current time step is not enough to get the full information of the environment. Therefore, integration of state information over multiple time steps captures the motion behavior, which is very important in the case of autonomous driving where the environmental state changes in split seconds. 

Thus, by adding recurrence, handling of POMDP (partially observable Markov decision process) ...

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