Skip to Main Content
Deep Reinforcement Learning Hands-On
book

Deep Reinforcement Learning Hands-On

by Oleg Vasilev, Maxim Lapan, Martijn van Otterlo, Mikhail Yurushkin, Basem O. F. Alijla
June 2018
Intermediate to advanced content levelIntermediate to advanced
546 pages
13h 30m
English
Packt Publishing
Content preview from Deep Reinforcement Learning Hands-On

Combining everything

We've now seen all DQN improvements mentioned in the paper [1] Rainbow: Combining Improvements in Deep Reinforcement Learning. Let's combine all of them into one hybrid method. First of all, we need to define our network architecture and the three methods that have contributed to it:

  • Categorical DQN: Our network will predict the value probability distribution of actions.
  • Dueling DQN: Our network will have two separate paths for value of state distribution and advantage distribution. On the output, both paths will be summed together, providing the final value probability distributions for actions. To force advantage distribution to have a zero mean, we'll subtract distribution with mean advantage in every atom.
  • NoisyNet: Our linear ...
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

Grokking Deep Reinforcement Learning

Grokking Deep Reinforcement Learning

Miguel Morales

Publisher Resources

ISBN: 9781788834247Supplemental Content