# A Heuristically Assisted Deep Reinforcement Learning Approach for Network Slice Placement

arXiv: https://arxiv.org/abs/2105.06741 · HTML: https://mlsanity.com/paper/2105.06741/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 42 references that are in the map.
- First posted on arXiv 14 May 2021.

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

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Tracking as Online Decision-Making: Learning a Policy from Streaming Videos with Reinforcement Learning](https://mlsanity.com/paper/1707.04991/) (2017)
- [Network Function Virtualization: State-of-the-art and Research Challenges](https://mlsanity.com/paper/1509.07675/) (2015)
- [Heuristic for Edge-enabled Network Slicing Optimization using the Power of Two Choices](https://mlsanity.com/paper/2010.08287/) (2020)

## Built on by (most cited first, 5 of 5)

- [DRL-based Slice Placement Under Non-Stationary Conditions](https://mlsanity.com/paper/2108.02495/) (2021)
- [On the Robustness of Controlled Deep Reinforcement Learning for Slice Placement](https://mlsanity.com/paper/2108.02505/) (2021)
- [Controlled Deep Reinforcement Learning for Optimized Slice Placement](https://mlsanity.com/paper/2108.01544/) (2021)
- [DRL-based Slice Placement under Realistic Network Load Conditions](https://mlsanity.com/paper/2109.12857/) (2021)
- [Robotic Test Tube Rearrangement Using Combined Reinforcement Learning and Motion Planning](https://mlsanity.com/paper/2401.09772/) (2024)

## Abstract (arXiv)

Network Slice placement with the problem of allocation of resources from a virtualized substrate network is an optimization problem which can be formulated as a multiobjective Integer Linear Programming (ILP) problem. However, to cope with the complexity of such a continuous task and seeking for optimality and automation, the use of Machine Learning (ML) techniques appear as a promising approach. We introduce a hybrid placement solution based on Deep Reinforcement Learning (DRL) and a dedicated optimization heuristic based on the Power of Two Choices principle. The DRL algorithm uses the so-called Asynchronous Advantage Actor Critic (A3C) algorithm for fast learning, and Graph Convolutional Networks (GCN) to automate feature extraction from the physical substrate network. The proposed Heuristically-Assisted DRL (HA-DRL) allows to accelerate the learning process and gain in resource usage when compared against other state-of-the-art approaches as the evaluation results evidence.