# OnSlicing: Online End-to-End Network Slicing with Reinforcement Learning

arXiv: https://arxiv.org/abs/2111.01616 · HTML: https://mlsanity.com/paper/2111.01616/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 57 references that are in the map.
- First posted on arXiv 2 Nov 2021.

## Builds on (most cited first, 18 of 18)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Towards Federated Learning at Scale: System Design](https://mlsanity.com/paper/1902.01046/) (2019)
- [Benchmarking Deep Reinforcement Learning for Continuous Control](https://mlsanity.com/paper/1604.06778/) (2016)
- [Advances in Variational Inference](https://mlsanity.com/paper/1711.05597/) (2017)
- [A Rewriting System for Convex Optimization Problems](https://mlsanity.com/paper/1709.04494/) (2017)
- [Constrained Reinforcement Learning Has Zero Duality Gap](https://mlsanity.com/paper/1910.13393/) (2019)
- [Learning Scheduling Algorithms for Data Processing Clusters](https://mlsanity.com/paper/1810.01963/) (2018)
- [Trial without Error: Towards Safe Reinforcement Learning via Human Intervention](https://mlsanity.com/paper/1707.05173/) (2017)
- [Hierarchical Imitation and Reinforcement Learning](https://mlsanity.com/paper/1803.00590/) (2018)
- [Multi-agent Reinforcement Learning for Networked System Control](https://mlsanity.com/paper/2004.01339/) (2020)
- [Constrained Deep Reinforcement Learning for Energy Sustainable Multi-UAV based Random Access IoT Networks with NOMA](https://mlsanity.com/paper/2002.00073/) (2020)
- [EdgeSlice: Slicing Wireless Edge Computing Network with Decentralized Deep Reinforcement Learning](https://mlsanity.com/paper/2003.12911/) (2020)
- [Sl-EDGE: Network Slicing at the Edge](https://mlsanity.com/paper/2005.00886/) (2020)
- [A Utility-Driven Multi-Queue Admission Control Solution for Network Slicing](https://mlsanity.com/paper/1901.06399/) (2019)
- [SDN Controllers: Benchmarking & Performance Evaluation](https://mlsanity.com/paper/1902.04491/) (2019)

## Built on by (most cited first, 7 of 7)

- [Advancing RAN Slicing with Offline Reinforcement Learning](https://mlsanity.com/paper/2312.10547/) (2023)
- [Generalizable Resource Scaling of 5G Slices using Constrained Reinforcement Learning](https://mlsanity.com/paper/2306.09290/) (2023)
- [Learning to Slice Wi-Fi Networks: A State-Augmented Primal-Dual Approach](https://mlsanity.com/paper/2405.05748/) (2024)
- [Atlas: Automate Online Service Configuration in Network Slicing](https://mlsanity.com/paper/2210.16902/) (2022)
- [SafeSlice: Enabling SLA-Compliant O-RAN Slicing via Safe Deep Reinforcement Learning](https://mlsanity.com/paper/2503.12753/) (2025)
- [AWaRe-SAC: Proactive Slice Admission Control under Weather-Induced Capacity Uncertainty](https://mlsanity.com/paper/2601.05978/) (2026)
- [BRAIN: Bayesian Reasoning via Active Inference for Agentic and Embodied Intelligence in Mobile Networks](https://mlsanity.com/paper/2602.14033/) (2026)

## Abstract (arXiv)

Network slicing allows mobile network operators to virtualize infrastructures and provide customized slices for supporting various use cases with heterogeneous requirements. Online deep reinforcement learning (DRL) has shown promising potential in solving network problems and eliminating the simulation-to-reality discrepancy. Optimizing cross-domain resources with online DRL is, however, challenging, as the random exploration of DRL violates the service level agreement (SLA) of slices and resource constraints of infrastructures. In this paper, we propose OnSlicing, an online end-to-end network slicing system, to achieve minimal resource usage while satisfying slices' SLA. OnSlicing allows individualized learning for each slice and maintains its SLA by using a novel constraint-aware policy update method and proactive baseline switching mechanism. OnSlicing complies with resource constraints of infrastructures by using a unique design of action modification in slices and parameter coordination in infrastructures. OnSlicing further mitigates the poor performance of online learning during the early learning stage by offline imitating a rule-based solution. Besides, we design four new domain managers to enable dynamic resource configuration in radio access, transport, core, and edge networks, respectively, at a timescale of subseconds. We implement OnSlicing on an end-to-end slicing testbed designed based on OpenAirInterface with both 4G LTE and 5G NR, OpenDayLight SDN platform, and OpenAir-CN core network. The experimental results show that OnSlicing achieves 61.3% usage reduction as compared to the rule-based solution and maintains nearly zero violation (0.06%) throughout the online learning phase. As online learning is converged, OnSlicing reduces 12.5% usage without any violations as compared to the state-of-the-art online DRL solution.