1 code implementation • 1 Mar 2024 • Thomas Firmin, Pierre Boulet, El-Ghazali Talbi
By defining an early stopping criterion detecting silent networks and by designing specific constraints, we were able to instantiate larger and more flexible search spaces.
no code implementations • 20 Feb 2024 • Halima Bouzidi, Smail Niar, Hamza Ouarnoughi, El-Ghazali Talbi
Our SONATA has seen up to sim$93. 6% Pareto dominance over the native NSGA-II, further stipulating the importance of self-adaptive evolution operators in HW-aware NAS.
Evolutionary Algorithms Hardware Aware Neural Architecture Search +1
1 code implementation • 21 Nov 2023 • Florian Felten, El-Ghazali Talbi, Grégoire Danoy
To tackle such an issue, this paper introduces multi-objective reinforcement learning based on decomposition (MORL/D), a novel methodology bridging the literature of RL and MOO.
Multi-Objective Reinforcement Learning reinforcement-learning
1 code implementation • 25 Oct 2023 • Florian Felten, Daniel Gareev, El-Ghazali Talbi, Grégoire Danoy
Hence, prior research has explored hyperparameter optimization in RL to address this concern.
Hyperparameter Optimization Multi-Objective Reinforcement Learning +1
2 code implementations • Conference on Neural Information Processing Systems Datasets and Benchmarks Track 2023 • Florian Felten, Lucas N. Alegre, Ann Nowé, Ana L. C. Bazzan, El-Ghazali Talbi, Grégoire Danoy, Bruno C. da Silva
Multi-objective reinforcement learning algorithms (MORL) extend standard reinforcement learning (RL) to scenarios where agents must optimize multiple---potentially conflicting---objectives, each represented by a distinct reward function.
no code implementations • 1 Jun 2023 • Juliette Gamot, Mathieu Balesdent, Romain Wuilbercq, Arnault Tremolet, Nouredine Melab, El-Ghazali Talbi
Balanced circular bin packing problems consist in positioning a given number of weighted circles in order to minimize the radius of a circular container while satisfying equilibrium constraints.
no code implementations • 27 Feb 2023 • Julie Keisler, El-Ghazali Talbi, Sandra Claudel, Gilles Cabriel
Based on this search space we propose neighbourhood and evolution search operators to optimize both the architecture and hyper-parameters of our networks.
no code implementations • 21 Dec 2022 • Juliette Gamot, Mathieu Balesdent, Arnault Tremolet, Romain Wuilbercq, Nouredine Melab, El-Ghazali Talbi
In order to tackle this NP-hard problem, a genetic algorithm enhanced by an adapted hidden-variables mechanism is proposed.
2 code implementations • Benelux Conference on Artificial Intelligence BNAIC/BeNeLearn 2022 • Lucas N. Alegre, Florian Felten, El-Ghazali Talbi, Grégoire Danoy, Ann Nowé, Ana L. C. Bazzan, Bruno C. da Silva
We introduce MO-Gym, an extensible library containing a diverse set of multi-objective reinforcement learning environments.
no code implementations • 20 Nov 2020 • El-Ghazali Talbi, Raca Todosijevic
More precisely, in the paper the so-called recovery-to-efficiency robustness concept is proposed and investigated.
no code implementations • 29 Jun 2020 • Ali Hebbal, Loic Brevault, Mathieu Balesdent, El-Ghazali Talbi, Nouredine Melab
Gaussian Processes (GPs) are one of the popular approaches to exhibit the correlations between these different fidelity levels.
no code implementations • 6 Mar 2020 • Julien Pelamatti, Loic Brevault, Mathieu Balesdent, El-Ghazali Talbi, Yannick Guerin
This results in an optimization problem for which the search space varies dynamically (with respect to both number and type of variables) along the optimization process as a function of the values of specific discrete decision variables.
no code implementations • 7 May 2019 • Ali Hebbal, Loic Brevault, Mathieu Balesdent, El-Ghazali Talbi, Nouredine Melab
To overcome this issue, a new Bayesian Optimization approach is proposed.
no code implementations • 13 Dec 2018 • Nicolas Dupin, El-Ghazali Talbi
It is shown that the restriction of time windows, which was used to ease computations, induces large over-costs and that this restriction is not required anymore with the capabilities of matheuristics or local search to solve such size of instances.