-
Notifications
You must be signed in to change notification settings - Fork 1
FassyGit/ReinforcementLearning_VIME
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
Main Changes (arguments): LIKELIHOOD_DS_BNN: 5.0 => 1.0 LR_BNN: 1e-4 => 1e-2 sample_pool_size: 10 => 5000 MAX_EPOCH_BNN: 1000 => 5 Main Changes (functionality): Enable training policy net on GPU Normalize test set if train set is normalized using same statistics Record detailed and informative values using tensorboard N of hidden units of policy net can be specified now Arguments to be tuned for different applications: ETA LR_BNN EXTRA_W_KL (Other arguments may also need to be tuned, but the effect of the listed ones could be more explainable and significant)
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published