Constrained Markov Decision Processes via Backward Value Functions
Example to run for PPO:
python train.py --num-steps 10 --num-episodes 1000 --eval-every 5 --log-every 5 --reset-dir --num-envs 1 --d0 5 --traj-len 10 --agent ppo --env pg --target
This repository has been archived by the owner on Jul 12, 2023. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 3
hercky/cmdps_via_bvf
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Constrained Markov Decision Processes via Backward Value Functions
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published