NMPA

Tensorflow implementation of Learning Non-myopic Power Allocation in Constrained Scenarios (https://arxiv.org/abs/)

Overview

This library contains a Tensorflow implementation of Learning Non-myopic Power Allocation in Constrained Scenarios as presented in [1](https://arxiv.org/abs/).

Dependencies

python>=3.6
tensorflow>=2.0: https://tensorflow.org
numpy
matplotlib

Structure

train: Code for training the NMPA model. Run as python3 train.py --set {expID} with default parameters.
model: Defines the NMPA model.
run: Code for running the trained NMPA model. Run as python3 run.py --set {expID} with default parameters.
train_uwmmmse: Code for training the lower-level UWMMSE model. Run as python3 train_uwmmse.py with default parameters.
data: Should contain your dataset in folder {expID}.
models: Stores pretrained models in a folder with same name as {expID}.
checkpoints: Stores trained models in a folder with same name as DDPG/{expID}.
results: Stores results in a folder with same name as {datset ID}.

Please cite [1] in your work when using this library in your experiments.

Feedback

For questions and comments, feel free to contact Arindam Chowdhury.

Citation

[1] Chowdhury A, Paternain S, Verma G, Swami A, Segarra S. Learning Non-myopic Power Allocation in Constrained Scenarios. 
arXiv preprint arXiv:.

BibTeX format:

@article{chowdhury2023deep,
  title={Learning Non-myopic Power Allocation in Constrained Scenarios},
  author={Chowdhury, Arindam and Paternain, Santiago and Verma, Gunjan and Swami, Ananthram and Segarra, Santiago},
  journal={arXiv e-prints},
  year={2023}
}

ArCho48 / NMPA