1. BENECHEHAB Abdelhakim
  2. BENECHEHAB Abdelhakim
print

BENECHEHAB Abdelhakim

Conference

Benechehab, Abdelhakim; Feofanov, Vasilii; Paolo, Giuseppe; Thomas, Albert; Filippone, Maurizio; Kégl, Balázs

AdaPTS: Adapting univariate foundation models to probabilistic multivariate time series forecasting

Submitted to ArXiV, 14 February 2025
Detail
ARXIV
BIBTEX

Conference

Zekri, Oussama; Odonnat, Ambroise; Benechehab, Abdelhakim; Bleistein, Linus; Boullé, Nicolas; Redko, Ievgen

Large language models as Markov chains

Submitted to ArXiV, 2 February 2025
Detail
ARXIV
BIBTEX

Poster / Demo

Benechehab, Abdelhakim; El Hili, Youssef Attia; Odonnat, Ambroise; Zekri, Oussama; Thomas, Albert; Paolo, Giuseppe; Filippone, Maurizio; Redko, Ievgen; Kégl, Balázs

Zero-shot model-based reinforcement learning using large language models

ICLR 2025, 13th International Conference on Learning Representations, 24-28 April 2025, Singapore, Singapore
Detail
Document
ARXIV
BIBTEX

Conference

Benechehab, Abdelhakim; Thomas, Albert; Paolo, Giuseppe; Filippone, Maurizio; Kégl, Balázs

A Study of the Weighted Multi-step Loss Impact on the Predictive Error and the Return in MBRL

RLC 2024, 1st Reinforcement Learning Conference, 9-12 August 2024, Amherst, MA, USA
Detail
Document
BIBTEX

Poster / Demo

Zekri, Oussama; Benechehab, Abdelhakim; Redko, Ievgen

Can LLMs predict the convergence of Stochastic Gradient Descent?

ICML 2024, 41st International Conference on Machine Learning, 1st ICML Workshop on In-Context Learning, 27 July 2024, Vienna, Austria
Detail
Document
ARXIV
BIBTEX

Poster / Demo

Thomas, Albert; Benechehab, Abdelhakim; Paolo, Giuseppe; Kégl, Balázs

Fair model-based reinforcement learning comparisons with explicit and consistent update frequency

ICLR 2024, 12th International Conference on Learning Representations, 3rd Blogpost Track, 7-11 May 2024, Vienna, Austria
Detail
BIBTEX

Journal

Benechehab, Abdelhakim; Thomas, Albert; Paolo, Giuseppe; Filippone, Maurizio; Kegl, Balazs

A multi-step loss function for robust learning of the dynamics in model-based reinforcement learning

Submitted to ArXiV, 5 February 2024
Detail
ARXIV
BIBTEX

Conference

Benechehab, Abdelhakim; Paolo, Giuseppe; Thomas, Albert; Filippone, Maurizio; Kégl, Balázs

Multi-timestep models for model-based reinforcement learning

Submitted to ArXiV, 11 October 2023
Detail
ARXIV
BIBTEX