# Knowledge-Assisted Deep Reinforcement Learning in 5G Scheduler Design: From Theoretical Framework to Implementation

arXiv: https://arxiv.org/abs/2009.08346 · HTML: https://mlsanity.com/paper/2009.08346/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2020.

## Built on by (most cited first, 8 of 8)

- [Online Reinforcement Learning in Non-Stationary Context-Driven Environments](https://mlsanity.com/paper/2302.02182/) (2023)
- [Demystifying Reinforcement Learning in Time-Varying Systems](https://mlsanity.com/paper/2201.05560/) (2022)
- [Learning Resource Scheduling with High Priority Users using Deep Deterministic Policy Gradients](https://mlsanity.com/paper/2304.09488/) (2023)
- [Reliable Projection Based Unsupervised Learning for Semi-Definite QCQP with Application of Beamforming Optimization](https://mlsanity.com/paper/2407.03668/) (2024)
- [Generalization Bounds for Transformer Channel Decoders](https://mlsanity.com/paper/2601.06969/) (2026)
- [Machine Learning for Massive Industrial Internet of Things](https://mlsanity.com/paper/2103.08308/) (2021)
- [A Distributed Neural Linear Thompson Sampling Framework to Achieve URLLC in Industrial IoT](https://mlsanity.com/paper/2401.06135/) (2023)
- [Graph Representation Learning for Contention and Interference Management in Wireless Networks](https://mlsanity.com/paper/2402.00879/) (2024)

## Abstract (arXiv)

In this paper, we develop a knowledge-assisted deep reinforcement learning (DRL) algorithm to design wireless schedulers in the fifth-generation (5G) cellular networks with time-sensitive traffic. Since the scheduling policy is a deterministic mapping from channel and queue states to scheduling actions, it can be optimized by using deep deterministic policy gradient (DDPG). We show that a straightforward implementation of DDPG converges slowly, has a poor quality-of-service (QoS) performance, and cannot be implemented in real-world 5G systems, which are non-stationary in general. To address these issues, we propose a theoretical DRL framework, where theoretical models from wireless communications are used to formulate a Markov decision process in DRL. To reduce the convergence time and improve the QoS of each user, we design a knowledge-assisted DDPG (K-DDPG) that exploits expert knowledge of the scheduler design problem, such as the knowledge of the QoS, the target scheduling policy, and the importance of each training sample, determined by the approximation error of the value function and the number of packet losses. Furthermore, we develop an architecture for online training and inference, where K-DDPG initializes the scheduler off-line and then fine-tunes the scheduler online to handle the mismatch between off-line simulations and non-stationary real-world systems. Simulation results show that our approach reduces the convergence time of DDPG significantly and achieves better QoS than existing schedulers (reducing 30% ~ 50% packet losses). Experimental results show that with off-line initialization, our approach achieves better initial QoS than random initialization and the online fine-tuning converges in few minutes.