Skip to content

Learning-Based Efficient Approximation of Data-enabled Predictive Control

License

Notifications You must be signed in to change notification settings

zhou-yh19/redpc

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

REDPC: A Real-time Efficient approximate DeePC

Python version

The code is tested with Python 3.10

Installation

pip install -r requirements.txt
git clone [email protected]:zhou-yh19/PyDeePC.git
cd PyDeePC
pip install -e .

Code structure

  • src/modules: PyTorch modules for approximating the scoring function
  • src/scripts: Scripts for data augmentation, and computing different scoring function
  • src/utils: Utility functions (customized PyTorch operations, tensor operations, etc.)
  • src/train.py: Training script for the scoring function
  • src/grid_train_one_gpu.py: Training script for the scoring function on a single GPU
  • experiments: Sample scripts for running experiments
  • test: julia scripts for testing solver

License

The project is released under the MIT license. See LICENSE for details.

Part of the project is modified from PyDeePC

About

Learning-Based Efficient Approximation of Data-enabled Predictive Control

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published