Skip to content

Instantly share code, notes, and snippets.

@lmclupr

lmclupr/lunar-lander-NN-network-TD0.ipynb

Created May 29, 2017 15:03
Show Gist options
  • Star 2 You must be signed in to star a gist
  • Fork 1 You must be signed in to fork a gist
  • Save lmclupr/d6a324cb330e887640b2cd852d0a2252 to your computer and use it in GitHub Desktop.
Save lmclupr/d6a324cb330e887640b2cd852d0a2252 to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
lunar-lander-NN-network-TD0.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@lmclupr
Copy link
Author

lmclupr commented May 29, 2017

Used TD(0) method to solve using the Lunar Lander V1. Used 4 individual feedforward neural networks (one per action) for function approximation using a Keras and Tensorflow stack.

@pablocastilla
Copy link

Clean and concise, superb!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment