# Deep Reinforcement Learning for Multi-Agent Power Control in Heterogeneous Networks

arXiv: https://arxiv.org/abs/2004.12095 · HTML: https://mlsanity.com/paper/2004.12095/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Apr 2020.

## Built on by (most cited first, 5 of 5)

- [Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey](https://mlsanity.com/paper/2110.13484/) (2021)
- [Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence](https://mlsanity.com/paper/2302.03322/) (2023)
- [Distributed-Training-and-Execution Multi-Agent Reinforcement Learning for Power Control in HetNet](https://mlsanity.com/paper/2212.07967/) (2022)
- [Novel Multi-Agent Action Masked Deep Reinforcement Learning for General Industrial Assembly Lines Balancing Problems](https://mlsanity.com/paper/2507.16635/) (2025)
- [LLM-Empowered Cooperative Content Caching in Vehicular Fog Caching-Assisted Platoon Networks](https://mlsanity.com/paper/2602.04471/) (2026)

## Abstract (arXiv)

We consider a typical heterogeneous network (HetNet), in which multiple access points (APs) are deployed to serve users by reusing the same spectrum band. Since different APs and users may cause severe interference to each other, advanced power control techniques are needed to manage the interference and enhance the sum-rate of the whole network. Conventional power control techniques first collect instantaneous global channel state information (CSI) and then calculate sub-optimal solutions. Nevertheless, it is challenging to collect instantaneous global CSI in the HetNet, in which global CSI typically changes fast. In this paper, we exploit deep reinforcement learning (DRL) to design a multi-agent power control algorithm in the HetNet. To be specific, by treating each AP as an agent with a local deep neural network (DNN), we propose a multiple-actor-shared-critic (MASC) method to train the local DNNs separately in an online trial-and-error manner. With the proposed algorithm, each AP can independently use the local DNN to control the transmit power with only local observations. Simulations results show that the proposed algorithm outperforms the conventional power control algorithms in terms of both the converged average sum-rate and the computational complexity.