This is an implementation of the Proximal Policy Optimization algorithm in PyTorch. It is built using actor critic and it learns how to play in the Vizdoom environment. By default it plays in deadly corridor, although the model is too simple to actually become proficient at playing, as I don't have the gpu power to train anything significant.
-
Notifications
You must be signed in to change notification settings - Fork 0
Gurnek/retro_ppo
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published