- Notifications
You must be signed in to change notification settings - Fork0
SCPO: Safe Reinforcement Learning with Safety Critic Policy Optimization
License
NotificationsYou must be signed in to change notification settings
SafeRL-Lab/SCPO
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
SCPO is a safe reinforcement learning algorithm. This repo is a fork ofStable Baselines3.
Note: Stable-Baselines3 supports PyTorch >= 1.11
SCPO requires Python 3.7+.
Install the Stable Baselines3 package:
pip install -r requirements.txtWe use environments from Bullet-Safety-Gym. Please follow the installation steps fromhttps://github.com/SvenGronauer/Bullet-Safety-Gym.
If you want to run pytorch in gpu mode, please install cuda and pytorch separatelyhttps://pytorch.org/
Example code for training can be found attrain.py. To train models with the best hyperparameters, please checktrain_best_hyper.py.
Checkplay.py.
 |  |
|---|---|
 |  |
If you find the repository useful, please cite the study
@article{mhamed2023scpo, title={SCPO: Safe Reinforcement Learning with Safety Critic Policy Optimization}, author={Mhamed, Jaafar and Gu, Shangding}, journal={arXiv preprint arXiv:2311.00880}, year={2023}}