https://github.com/lovelybuggies/mfg-pigno
https://github.com/lovelybuggies/mfg-pigno
Last synced: about 1 month ago
JSON representation
- Host: GitHub
- URL: https://github.com/lovelybuggies/mfg-pigno
- Owner: LovelyBuggies
- Created: 2023-07-30T14:03:02.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-04-01T03:53:57.000Z (about 1 year ago)
- Last Synced: 2025-02-08T10:45:18.420Z (3 months ago)
- Language: Python
- Size: 399 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# MFG-PIGN
To use MPNN and physic loss to predict the MFG.
rho_{i,t}=rho_{i,t-1}+rho_{i-1,t-1}u_{i-1,t-1}-rho_{i,t-1}u_{i,t-1}.
To run:
```
python3 main.y --network braess --config_path config/braess/braess-simple.ymal
```
Citation:
```
@Article{g15020012,
AUTHOR = {Chen, Xu and Liu, Shuo and Di, Xuan},
TITLE = {Physics-Informed Graph Neural Operator for Mean Field Games on Graph: A Scalable Learning Approach},
JOURNAL = {Games},
VOLUME = {15},
YEAR = {2024},
NUMBER = {2},
ARTICLE-NUMBER = {12},
URL = {https://www.mdpi.com/2073-4336/15/2/12},
ISSN = {2073-4336},
DOI = {10.3390/g15020012}
}
```