Deep Reinforcement Learning Based Power control for Wireless Multicast Systems
Networking and Internet Architecture
2019-10-25 v2 Machine Learning
Machine Learning
Abstract
We consider a multicast scheme recently proposed for a wireless downlink in [1]. It was shown earlier that power control can significantly improve its performance. However for this system, obtaining optimal power control is intractable because of a very large state space. Therefore in this paper we use deep reinforcement learning where we use function approximation of the Q-function via a deep neural network. We show that optimal power control can be learnt for reasonably large systems via this approach. The average power constraint is ensured via a Lagrange multiplier, which is also learnt. Finally, we demonstrate that a slight modification of the learning algorithm allows the optimal control to track the time varying system statistics.
Cite
@article{arxiv.1910.05308,
title = {Deep Reinforcement Learning Based Power control for Wireless Multicast Systems},
author = {Ramkumar Raghu and Pratheek Upadhyaya and Mahadesh Panju and Vaneet Aggarwal and Vinod Sharma},
journal= {arXiv preprint arXiv:1910.05308},
year = {2019}
}