Implementation of vanilla stochaistic (categorical) policy gradient algorithm to play cartpole.
Vanilla policy gradient takes longer but convergence is smoother than DQN for the cartpole, both of these properties as expected.
-
Notifications
You must be signed in to change notification settings - Fork 2
shivamsaboo17/Policy-Gradient-PyTorch
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Implementation of vanilla stochaistic (categorical) policy gradient algorithm to play cartpole.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published