# Deep Reinforcement Learning for Wireless Resource Allocation Using Buffer State Information

arXiv: https://arxiv.org/abs/2108.12198 · HTML: https://mlsanity.com/paper/2108.12198/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 22 references that are in the map.
- First posted on arXiv 27 Aug 2021.

## Builds on (most cited first, 6 of 6)

- [Applications of Deep Reinforcement Learning in Communications and Networking: A Survey](https://mlsanity.com/paper/1810.07862/) (2018)
- [Kickstarting Deep Reinforcement Learning](https://mlsanity.com/paper/1803.03835/) (2018)
- [Ultra-Reliable and Low-Latency Wireless Communication: Tail, Risk and Scale](https://mlsanity.com/paper/1801.01270/) (2018)
- [Learn to Schedule (LEASCH): A Deep reinforcement learning approach for radio resource scheduling in the 5G MAC layer](https://mlsanity.com/paper/2003.11003/) (2020)
- [Deep Reinforcement Learning for Scheduling in Cellular Networks](https://mlsanity.com/paper/1905.05914/) (2019)
- [Buffer-aware Wireless Scheduling based on Deep Reinforcement Learning](https://mlsanity.com/paper/1911.05281/) (2019)

## Built on by (most cited first, 1 of 1)

- [Deep Reinforcement Learning for Uplink Multi-Carrier Non-Orthogonal Multiple Access Resource Allocation Using Buffer State Information](https://mlsanity.com/paper/2208.14689/) (2022)

## Abstract (arXiv)

As the number of user equipments (UEs) with various data rate and latency requirements increases in wireless networks, the resource allocation problem for orthogonal frequency-division multiple access (OFDMA) becomes challenging. In particular, varying requirements lead to a non-convex optimization problem when maximizing the systems data rate while preserving fairness between UEs. In this paper, we solve the non-convex optimization problem using deep reinforcement learning (DRL). We outline, train and evaluate a DRL agent, which performs the task of media access control scheduling for a downlink OFDMA scenario. To kickstart training of our agent, we introduce mimicking learning. For improvement of scheduling performance, full buffer state information at the base station (e.g. packet age, packet size) is taken into account. Techniques like input feature compression, packet shuffling and age capping further improve the performance of the agent. We train and evaluate our agents using Nokia's wireless suite and evaluate against different benchmark agents. We show that our agents clearly outperform the benchmark agents.