# Percentile-Based Deep Reinforcement Learning and Reward Based Personalization For Delay Aware RAN Slicing in O-RAN

arXiv: https://arxiv.org/abs/2507.18111 · HTML: https://mlsanity.com/paper/2507.18111/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 19 of its 44 references that are in the map.
- First posted on arXiv 24 Jul 2025.

## Placed in

- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Builds on (most cited first, 19 of 19)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Personalized Cross-Silo Federated Learning on Non-IID Data](https://mlsanity.com/paper/2007.03797/) (2020)
- [Understanding O-RAN: Architecture, Interfaces, Algorithms, Security, and Research Challenges](https://mlsanity.com/paper/2202.01032/) (2022)
- [Intelligence and Learning in O-RAN for Data-driven NextG Cellular Networks](https://mlsanity.com/paper/2012.01263/) (2020)
- [5G Wireless Network Slicing for eMBB, URLLC, and mMTC: A Communication-Theoretic View](https://mlsanity.com/paper/1804.05057/) (2018)
- [Intelligent O-RAN for Beyond 5G and 6G Wireless Networks](https://mlsanity.com/paper/2005.08374/) (2020)
- [Dynamic RAN Slicing for Service-Oriented Vehicular Networks via Constrained Learning](https://mlsanity.com/paper/2012.01991/) (2020)
- [Dynamic SDN-based Radio Access Network Slicing with Deep Reinforcement Learning for URLLC and eMBB Services](https://mlsanity.com/paper/2202.06435/) (2022)
- [Federated Deep Reinforcement Learning for Open RAN Slicing in 6G Networks](https://mlsanity.com/paper/2206.11328/) (2022)
- [Programmable and Customized Intelligence for Traffic Steering in 5G Networks Using Open RAN Architectures](https://mlsanity.com/paper/2209.14171/) (2022)
- [Colosseum: Large-Scale Wireless Experimentation Through Hardware-in-the-Loop Network Emulation](https://mlsanity.com/paper/2110.10617/) (2021)
- [OrchestRAN: Network Automation through Orchestrated Intelligence in the Open RAN](https://mlsanity.com/paper/2201.05632/) (2022)
- [On the Specialization of FDRL Agents for Scalable and Distributed 6G RAN Slicing Orchestration](https://mlsanity.com/paper/2211.03088/) (2022)
- [Queue-Learning: A Reinforcement Learning Approach for Providing Quality of Service](https://mlsanity.com/paper/2101.04627/) (2021)
- [Federated Deep Reinforcement Learning for the Distributed Control of NextG Wireless Networks](https://mlsanity.com/paper/2112.03465/) (2021)
- [Energy-aware Scheduling of Virtualized Base Stations in O-RAN with Online Learning](https://mlsanity.com/paper/2208.09956/) (2022)
- [Machine Learning-based Early Attack Detection Using Open RAN Intelligent Controller](https://mlsanity.com/paper/2302.01864/) (2023)
- [RAN Slicing for Massive IoT and Bursty URLLC Service Multiplexing: Analysis and Optimization](https://mlsanity.com/paper/2001.04161/) (2020)
- [Energy Saving and Traffic Steering Use Case and Testing by O-RAN RIC xApp/rApp Multi-vendor Interoperability](https://mlsanity.com/paper/2409.19807/) (2024)

## Abstract (arXiv)

In this paper, we tackle the challenge of radio access network (RAN) slicing within an open RAN (O-RAN) architecture. Our focus centers on a network that includes multiple mobile virtual network operators (MVNOs) competing for physical resource blocks (PRBs) with the goal of meeting probabilistic delay upper bound constraints for their clients while minimizing PRB utilization. Initially, we derive a reward function based on the law of large numbers (LLN), then implement practical modifications to adapt it for real-world experimental scenarios. We then propose our solution, the Percentile-based Delay-Aware Deep Reinforcement Learning (PDA-DRL), which demonstrates its superiority over several baselines, including DRL models optimized for average delay constraints, by achieving a 38% reduction in resultant average delay. Furthermore, we delve into the issue of model weight sharing among multiple MVNOs to develop a robust personalized model. We introduce a reward-based personalization method where each agent prioritizes other agents' model weights based on their performance. This technique surpasses traditional aggregation methods, such as federated averaging, and strategies reliant on traffic patterns and model weight distance similarities.