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

Architecture and properties of AlphaGo Zero

There were five changes from the previous version of AlphaGo. They were as follows:

  • Trains entirely from self play that is no human experts game play data and learning everything from scratch. Earlier versions had supervised learning policy networks, which was trained on expert game plays.
  • No hand-crafted features.
  • Replaced the normal convolution architecture with residual convolution architecture.
  • Instead of a separate policy and value network, AlphaGo Zero has combined both of them into a single large network.
  • Simplified the Monte Carlo Tree Search, which uses this large neural network for simulations.

The network input consists of:

  • 19 x 19 matrix plane representing the board of Go
  • One feature ...
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