BUP is an uncertainty-based offline RL algorithm based on TD3 algorithm.
This code is built on the official TD3_BC repository and referred to the EDAC code for ensemble critic.
Running main_uncertain.py to reproduce the results in the paper:
-
Notifications
You must be signed in to change notification settings - Fork 0
qsa-fox/bup
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Pessimistic policy iteration with bounded uncertainty
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published