A Digital Twin-Based Deep Reinforcement Learning Framework for Adaptive Scheduling in 5G/6G Networks
The transition toward AI-native 6G networks requires intelligent, adaptive, and reliable control mechanisms capable of handling highly dynamic and heterogeneous environments. In this context, reinforcement learning has emerged as a promising approach for optimizing network performance. However, existing works often focus on algorithmic design while overlooking critical aspects such as experimental rigor, reward formulation, and reproducibility, which can significantly impact the validity of the results. This paper proposes a Digital Twin-based Deep Reinforcement Learning framework for adaptive scheduling in 5G networks, where the twin is implemented as a simulation-driven proxy. Within this framework, a Deep Q-Network agent dynamically selects transmission interval configurations to jointly optimize key Quality of Service metrics. A key contribution of this work lies in the systematic identification and correction of critical experimental issues, including reward degeneracy and hidden coupling between control variables, which are often neglected in RL-based networking studies. To ensure robustness, the proposed approach incorporates multi-seed statistical evaluation, providing reproducible and reliable performance assessment. Experimental results demonstrate that the proposed DRL agent consistently converges toward the optimal scheduling configuration and achieves stable performance across multiple runs, outperforming a tabular Q-learning baseline.