-This project inolved applied Reinfocrcement learnging viz,. Deep Q Learning for the 'cart' to learn to balance the pole. -Uses Open AI Gym CartPole-v0 environment. -Built the deep convolutional neural netork with PyTorch. -The CNN is used as a approximator to predict the optimal action given a set of images as inputs states. (the state that the game is in) -Code is directed to run on GPU. -Feel free to clone/download or even contribute. CHEERS!
-
Notifications
You must be signed in to change notification settings - Fork 0
naman4real/CartPole-ReinforcementLearning
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
This project inolved applied Reinfocrcement learnging viz,. Deep Q Learning for the 'cart' to learn to balance the 'pole'
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published