Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Alessandro Lazaric

Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret


Apr 22, 2021
Jean Tarbouriech, Runlong Zhou, Simon S. Du, Matteo Pirotta, Michal Valko, Alessandro Lazaric


  Access Paper or Ask Questions

Leveraging Good Representations in Linear Contextual Bandits


Apr 08, 2021
Matteo Papini, Andrea Tirinzoni, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta


  Access Paper or Ask Questions

Reinforcement Learning with Prototypical Representations


Feb 22, 2021
Denis Yarats, Rob Fergus, Alessandro Lazaric, Lerrel Pinto


  Access Paper or Ask Questions

Improved Sample Complexity for Incremental Autonomous Exploration in MDPs


Dec 29, 2020
Jean Tarbouriech, Matteo Pirotta, Michal Valko, Alessandro Lazaric

* NeurIPS 2020 

  Access Paper or Ask Questions

An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits


Oct 23, 2020
Andrea Tirinzoni, Matteo Pirotta, Marcello Restelli, Alessandro Lazaric

* To appear at NeurIPS 2020 

  Access Paper or Ask Questions

Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration


Aug 18, 2020
Andrea Zanette, Alessandro Lazaric, Mykel J. Kochenderfer, Emma Brunskill


  Access Paper or Ask Questions

Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation


Jul 13, 2020
Marc Abeille, Alessandro Lazaric


  Access Paper or Ask Questions

A Provably Efficient Sample Collection Strategy for Reinforcement Learning


Jul 13, 2020
Jean Tarbouriech, Matteo Pirotta, Michal Valko, Alessandro Lazaric


  Access Paper or Ask Questions

Improved Analysis of UCRL2 with Empirical Bernstein Inequality


Jul 10, 2020
Ronan Fruit, Matteo Pirotta, Alessandro Lazaric

* Document in support of the tutorial at ALT 2019 

  Access Paper or Ask Questions

A Novel Confidence-Based Algorithm for Structured Bandits


May 23, 2020
Andrea Tirinzoni, Alessandro Lazaric, Marcello Restelli

* AISTATS 2020 

  Access Paper or Ask Questions

Meta-learning with Stochastic Linear Bandits


May 18, 2020
Leonardo Cella, Alessandro Lazaric, Massimiliano Pontil


  Access Paper or Ask Questions

Learning Adaptive Exploration Strategies in Dynamic Environments Through Informed Policy Regularization


May 06, 2020
Pierre-Alexandre Kamienny, Matteo Pirotta, Alessandro Lazaric, Thibault Lavril, Nicolas Usunier, Ludovic Denoyer

* 18 pages 

  Access Paper or Ask Questions

Active Model Estimation in Markov Decision Processes


Mar 06, 2020
Jean Tarbouriech, Shubhanshu Shekhar, Matteo Pirotta, Mohammad Ghavamzadeh, Alessandro Lazaric


  Access Paper or Ask Questions

Learning Near Optimal Policies with Low Inherent Bellman Error


Mar 05, 2020
Andrea Zanette, Alessandro Lazaric, Mykel Kochenderfer, Emma Brunskill

* Minor fix 

  Access Paper or Ask Questions

Near-linear Time Gaussian Process Optimization with Adaptive Batching and Resparsification


Feb 26, 2020
Daniele Calandriello, Luigi Carratino, Alessandro Lazaric, Michal Valko, Lorenzo Rosasco


  Access Paper or Ask Questions

Adversarial Attacks on Linear Contextual Bandits


Feb 11, 2020
Evrard Garcelon, Baptiste Roziere, Laurent Meunier, Jean Tarbouriech, Olivier Teytaud, Alessandro Lazaric, Matteo Pirotta


  Access Paper or Ask Questions

Improved Algorithms for Conservative Exploration in Bandits


Feb 08, 2020
Evrard Garcelon, Mohammad Ghavamzadeh, Alessandro Lazaric, Matteo Pirotta


  Access Paper or Ask Questions

Conservative Exploration in Reinforcement Learning


Feb 08, 2020
Evrard Garcelon, Mohammad Ghavamzadeh, Alessandro Lazaric, Matteo Pirotta


  Access Paper or Ask Questions

Concentration Inequalities for Multinoulli Random Variables


Jan 30, 2020
Jian Qian, Ronan Fruit, Matteo Pirotta, Alessandro Lazaric

* Tutorial at ALT'19 on Regret Minimization in Infinite-Horizon Finite Markov Decision Processes 

  Access Paper or Ask Questions

No-Regret Exploration in Goal-Oriented Reinforcement Learning


Jan 30, 2020
Jean Tarbouriech, Evrard Garcelon, Michal Valko, Matteo Pirotta, Alessandro Lazaric


  Access Paper or Ask Questions

Frequentist Regret Bounds for Randomized Least-Squares Value Iteration


Nov 01, 2019
Andrea Zanette, David Brandfonbrener, Matteo Pirotta, Alessandro Lazaric


  Access Paper or Ask Questions

A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning


Oct 19, 2019
Nicolas Carion, Gabriel Synnaeve, Alessandro Lazaric, Nicolas Usunier

* NeurIPS 2019 

  Access Paper or Ask Questions

Word-order biases in deep-agent emergent communication


Jun 14, 2019
Rahma Chaabouni, Eugene Kharitonov, Alessandro Lazaric, Emmanuel Dupoux, Marco Baroni

* Conference: Association for Computational Linguistics (ACL) 

  Access Paper or Ask Questions

Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret


Mar 13, 2019
Daniele Calandriello, Luigi Carratino, Alessandro Lazaric, Michal Valko, Lorenzo Rosasco


  Access Paper or Ask Questions

Active Exploration in Markov Decision Processes


Feb 28, 2019
Jean Tarbouriech, Alessandro Lazaric


  Access Paper or Ask Questions