Efppo
No description available
Install / Use
/learn @MIT-REALM/EfppoREADME
<div align="center">
Epigraphic Form Proximal Policy Optimization (EFPPO)
</div> <p align="center"> <img src="https://upload.wikimedia.org/wikipedia/commons/c/ca/1x1.png" width="16%" /> <img src="https://raw.githubusercontent.com/MIT-REALM/efppo/website/public/media/hopper.gif" width="32%" />   <img src="https://raw.githubusercontent.com/MIT-REALM/efppo/website/public/media/f16.gif" width="32%" /> <img src="https://upload.wikimedia.org/wikipedia/commons/c/ca/1x1.png" width="16%" /> </p> <div align="center">Solving Stabilize-Avoid Optimal Control via Epigraph Form and Deep Reinforcement Learning
Webpage • arXiv • Paper ❘ Installation • Getting started • Citation
</div>Installation
This is a JAX-based project. To install, install jax first and other prereqs following their instructions.
Next, clone the repository and install the package.
git clone https://github.com/mit-realm/efppo.git
cd efppo
pip install -e .
Getting started
Example:
python python scripts/train_dbint_inner.py --name run1
python scripts/eval_dbint_rootfind.py runs/DbInt_inner/00001-run1/ckpts/00099999/default
<div align="center">
<img src="media/dbint_example.jpg" width="50%" />
</div>
Citation
Please cite the EFPPO paper.
@inproceedings{so2023solving,
AUTHOR = {Oswin So AND Chuchu Fan},
TITLE = {{Solving Stabilize-Avoid Optimal Control via Epigraph Form and Deep Reinforcement Learning}},
BOOKTITLE = {Proceedings of Robotics: Science and Systems},
YEAR = {2023},
MONTH = {July},
DOI = {10.15607/RSS.2023.XIX.085}
}
