This repository is the official implementation of Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks.
📋 Project website: HiT-MAC
If you want to try your own algorithm in our environment, here is a pure and non-hierarchical DSN environment for you.
To install requirements:
pip install -r requirements.txt
To train the executor in the paper, run this command:
python main.py --env Pose-v0 --model single-att --workers 6
To train the coordinator in the paper, run this command:
python main.py --env Pose-v1 --model multi-att-shap --workers 6
To evaluate my model, run:
python main.py --env Pose-v1 --model multi-att-shap --workers 0 --load-coordinator-dir trainedModel/best_coordinator.pth --load-executor-dir trainedModel/best_executor.pth
You can use trained models directly from the folder "trainedModel".
If you found this work useful, please consider citing:
@article{xu2020learning,
title={Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks},
author={Xu, Jing and Zhong, Fangwei and Wang, Yizhou},
journal={Advances in Neural Information Processing Systems},
volume={33},
year={2020}
}
If you have any suggestion/questions, get in touch at [email protected]
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent