Skip to content

NPLawrence/RL-MPC

Repository files navigation

Goal-conditioned RL meets robust MPC

Code for the paper A view on learning robust goal-conditioned value functions: Interplay between RL and MPC.

Alt text

Requirements

Code was developed using Python 3.9.6. In a virtual environment, run:

pip install -r requirements.txt

To recreate figures, the data is in misc, which you will need to unzip and put into a new folder "data" in the main directory. The plotting functions are in eval.

Citation

Please cite our work using the following bib entry:

@article{lawrence2025view,
  title={A view on learning robust goal-conditioned value functions: Interplay between {RL} and {MPC}},
  author={Lawrence, Nathan P and Loewen, Philip D and Forbes, Michael G and Gopaluni, R Bhushan and Mesbah, Ali},
  journal={Annual Reviews in Control},
  year={2025},
  doi = {https://doi.org/10.1016/j.arcontrol.2025.101027}
}

About

Implementation of value function-augmented MPC

Topics

Resources

License

Stars

Watchers

Forks

Contributors

Languages