no code implementations • NeurIPS 2020 • Elena Smirnova, Elvis Dohmatob
Entropy regularization, smoothing of Q-values and neural network function approximator are key components of the state-of-the-art reinforcement learning (RL) algorithms, such as Soft Actor-Critic~\cite{haarnoja2018soft}.
no code implementations • 20 Sep 2019 • Elena Smirnova, Elvis Dohmatob
Entropy regularized algorithms such as Soft Q-learning and Soft Actor-Critic, recently showed state-of-the-art performance on a number of challenging reinforcement learning (RL) tasks.
no code implementations • 14 Jun 2019 • Louis Faury, Ugo Tanielian, Flavian vasile, Elena Smirnova, Elvis Dohmatob
This manuscript introduces the idea of using Distributionally Robust Optimization (DRO) for the Counterfactual Risk Minimization (CRM) problem.
no code implementations • 23 Feb 2019 • Elena Smirnova, Elvis Dohmatob, Jérémie Mary
Our formulation results in a efficient algorithm that accounts for a simple re-weighting of policy actions in the standard policy iteration scheme.
no code implementations • 7 Sep 2018 • Elena Smirnova
In this paper, we consider interactions triggered by the recommendations of deployed recommender system in addition to browsing behavior.
no code implementations • 23 Jul 2018 • Kiewan Villatel, Elena Smirnova, Jérémie Mary, Philippe Preux
Recommender systems objectives can be broadly characterized as modeling user preferences over short-or long-term time horizon.
1 code implementation • 23 Jun 2017 • Elena Smirnova, Flavian vasile
Recommendations can greatly benefit from good representations of the user state at recommendation time.
2 code implementations • 25 Jul 2016 • Flavian Vasile, Elena Smirnova, Alexis Conneau
We propose Meta-Prod2vec, a novel method to compute item similarities for recommendation that leverages existing item metadata.