A Heuristically Assisted Deep Reinforcement Learning Approach for Network Slice Placement

Amina Boubendir; Fabrice Guillemin; Jose Jurandir Alves Esteves; Pierre Sens

RECORD

A Heuristically Assisted Deep Reinforcement Learning Approach for Network Slice Placement

Jose Jurandir Alves Esteves, Amina Boubendir, Fabrice Guillemin, Pierre Sens

Networking and Internet Architecture · Submitted 14 May 2021

abstract compiled · 2026-09-23 · no language-model review

The authors' main claim 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.

how it is stated · asserted 0.98 read the record →

Comment (0) Read on arXiv ↗

Cite ▾

arXiv ID2105.06741 (version 1)

Pith ID2HYRNWIL, Pith's permanent record of this paper and its review

CitationAmina Boubendir, Fabrice Guillemin, Jose Jurandir Alves Esteves, Pierre Sens. "A Heuristically Assisted Deep Reinforcement Learning Approach for Network Slice Placement." arXiv:2105.06741 (2021). https://pith.science/paper/2HYRNWIL

Claim paper

The compiled record

The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.

Open the compiled record

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-09-23: 1 request, 4,409 input tokens.

What the abstract itself states, as probabilities: claims first 0.05 · states limitation 0.08 · human participants 0.02 · controlled comparison 0.68 · randomized assignment 0.02 · states quantitative result 0.05 · compares with prior results 0.94 · mentions code or data availability 0.02.

The abstract, sentence by sentence

arXiv listing abstract v1. Results and the main claim are underlined; show every role.

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.

background contribution method result interpretation main claim

What the classifier reports for each sentence. The number is the probability it gave the label.
#	sentence	role	the authors' own work	states the main conclusion	strength
s0	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.	background 1.00	0.09	0.03	asserted 1.00
s1	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.	background 0.83	0.06	0.04	hedged possibility 0.88
s2	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.	contribution 0.84	0.90	0.10	asserted 0.99
s3	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.	method 1.00	0.76	0.04	asserted 1.00
s4	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.	result 0.83	0.92	0.85	asserted 0.98

What kind of paper the classifier reports this is: method or tool 1.00 · evidence from simulation or computation 0.86.

What was examined, and what was not

sources read

arXiv listing abstract v1

not examined

full text
figures and tables
references and citing sentences
relations to other papers

levels run

P abstract

not run

S sections
T body sentences
C citations
R cross-paper relations

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. Every number in the measurements table is the authors', checked by code. Record as JSON

The paper

Original abstract

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.

Human review

How Pith checks papers → · Full audit of this paper →

How the literature uses it

4 arXiv papers cite this in 36 sentences

Each citing sentence is taken from the citing paper's LaTeX source and typed by Pith's classifier. A label appears at probability 0.8 or more (0.95 for support), a contest at 0.7 or more; the quoted words are the citing authors'. How each label was checked · JSON

Papers whose main result relates to this one's

Found among the papers closest to this one by title and main claim. Pith's classifier compared each pair's main results and a second model family confirmed the relation; checked against two further families, shown conflicts agreed 118 times in 120 and shown same results 218 times in 239. The quoted sentence is the other paper's main claim.

States the same result 1 paper

The evaluation results show that the proposed HA-DRL algorithm can accelerate the learning of an efficient slice placement policy improving slice acceptance ratio when compared with state-of-the-art approaches that are based only on reinforcement learning.

Controlled Deep Reinforcement Learning for Optimized Slice Placement · 0.97

Papers citing it · 12 sentences without a confident label

Builds on it 1 paper

To cope with traffic changes, we propose in the present paper to extend a hybrid DRL-heuristic algorithm we have recently introduced in [ref] (namely Heuristically Assisted DRL, HA-DRL) to evaluate the performance under non-stationary network loads.

DRL-based Slice Placement Under Non-Stationary Conditions · Introduction · 1.00

Uses its method or tool 3 papers

We reuse the framework introduced in [ref] .

On the Robustness of Controlled Deep Reinforcement Learning for Slice Placement · Policy · 0.99
We describe the Heuristically Assisted DRL (HA-DRL) introduced in [ref] to specifically address the challenge of obtaining a better and explainable behavior of DRL agents.

Controlled Deep Reinforcement Learning for Optimized Slice Placement · Introduction · 0.80
We reuse the framework introduced in [ref] .

DRL-based Slice Placement Under Non-Stationary Conditions · Policy · 0.97

Cites it as support 1 paper

This is due to the fact that the strong influence of the Heuristic Function helps the algorithm to become stable more quickly as discussed in [ref] and [ref] .

On the Robustness of Controlled Deep Reinforcement Learning for Slice Placement · Evaluation of the impact of network load change · 0.97

Cites it as background 4 papers

The interested reader may refer to [ref] for a more detailed and comprehensive discussion.

On the Robustness of Controlled Deep Reinforcement Learning for Slice Placement · Related Work Analysis · 0.93
A complete model description and problem formulation can be found in [ref] and [ref] .

Controlled Deep Reinforcement Learning for Optimized Slice Placement · Network Slice Placement Optimization problem · 0.85
The reader interested in a more detailed and comprehensive discussion of those works cited in the present paper may refer to [ref] .

DRL-based Slice Placement Under Non-Stationary Conditions · Related Work Analysis · 0.92

Discussion

Know something about this paper? Leave a comment, or highlight any passage above to comment on it.