O'Reilly logo

Deep Reinforcement Learning Hands-On by Maxim Lapan

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

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 ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required