Published in The International Conference on Learning Representations, 2021
Recommended citation: Yannis Flet-Berliac, Reda Ouhamma, Odalric-Ambrym Maillard, and Philippe Preux. "Learning value functions in deep policy gradients using residual variance." International Conference on Learning Representations. 2021.
Published in Neural Information Processing Systems 34, 2021
Recommended citation: Reda Ouhamma, Odalric-Ambrym Maillard, and Vianney Perchet. "Stochastic Online Linear Regression: the Forward Algorithm to Replace Ridge." Advances in Neural Information Processing Systems 34 (2021): 24430-24441.
Published in Neural Information Processing Systems 34, Spotlight (top 3%), 2021
Recommended citation: Reda Ouhamma, Rémy Degenne, Vianney Perchet, and Pierre Gaillard. "Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits." Advances in Neural Information Processing Systems 34 (2021): 18577-18589.
Published in The AAAI Conference on Artificial Intelligence, 2023
Recommended citation: Reda Ouhamma, Debabrota Basu, and Odalric-Ambrym Maillard. "Bilinear exponential family of mdps: Frequentist regret bound with tractable exploration and planning." AAAI (2023).
Published:
I presented my work on online sign identification in the bandit setting at the Inria Lille seminar. Slides
Published:
I was invited to present my paper on stochastic online regression at the MIA departement’s seminar. Slides
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.
