Odalric-Ambrym Maillard

90
Documents

Publications

27
5
3
3
1
1
1
1
1

Publications

Deposit thumbnail

The Confusing Instance Principle for Online Linear Quadratic Control

Waris Radji , Odalric-Ambrym Maillard

Reinforcement Learning Journal, 2025, 6, pp.811-828

Article dans une revue hal-05322160v1
Deposit thumbnail

Leveraging priors on distribution functions for multi-arm bandits

Sumit Vashishtha , Odalric-Ambrym Maillard

Reinforcement Learning Journal, In press, 6, pp.1600-1623. ⟨10.48550/arXiv.2503.04518⟩

Article dans une revue hal-05310340v1
Deposit thumbnail

Bandits with Stochastic Corruption: Lower Bounds on Regret and Robust Optimistic Algorithms

Timothée Mathieu , Debabrota Basu , Odalric-Ambrym Maillard

Transactions on Machine Learning Research Journal, 2024

Article dans une revue hal-04615733v2
Deposit thumbnail

AdaStop: adaptive statistical testing for sound comparisons of Deep RL agents

Timothée Mathieu , Riccardo Della Vecchia , Alena Shilova , Matheus Medeiros Centa , Hector Kohler et al.

Transactions on Machine Learning Research Journal, 2024

Article dans une revue hal-04132861v2
Deposit thumbnail

Local Dvoretzky-Kiefer-Wolfowitz confidence bands

Odalric-Ambrym Maillard

Mathematical Methods of Statistics, 2022, ⟨10.3103/S1066530721010038⟩

Article dans une revue hal-03780573v1
Deposit thumbnail

Reinforcement Learning for crop management

Romain Gautron , Odalric-Ambrym Maillard , Philippe Preux , Marc Corbeels , Régis Sabbadin

Computers and Electronics in Agriculture, 2022, 200, pp.107182. ⟨10.1016/j.compag.2022.107182⟩

Article dans une revue hal-03834290v1

A channel selection game for multi-operator LoRaWAN deployments

Kinda Khawam , Hassan Fawaz , Samer Lahoud , Odalric-Ambrym Maillard , Steven Martin

Computer Networks, 2022, 216, pp.109185. ⟨10.1016/j.comnet.2022.109185⟩

Article dans une revue hal-03937953v1
Deposit thumbnail

Efficient Change-Point Detection for Tackling Piecewise-Stationary Bandits

Lilian Besson , Emilie Kaufmann , Odalric-Ambrym Maillard , Julien Seznec

Journal of Machine Learning Research, 2022

Article dans une revue hal-02006471v3
Deposit thumbnail

Collaborative Algorithms for Online Personalized Mean Estimation

Mahsa Asadi , Aurélien Bellet , Odalric-Ambrym Maillard , Marc Tommasi

Transactions on Machine Learning Research Journal, 2022

Article dans une revue hal-03905917v1
Deposit thumbnail

Boundary Crossing Probabilities for General Exponential Families

Odalric-Ambrym Maillard

Mathematical Methods of Statistics, 2018, 27, pp.1-31. ⟨10.3103/S1066530718010015⟩

Article dans une revue hal-01737150v1
Deposit thumbnail

Streaming kernel regression with provably adaptive mean, variance, and regularization

Audrey Durand , Odalric-Ambrym Maillard , Joelle Pineau

Journal of Machine Learning Research, 2018, 1, pp.1 - 48

Article dans une revue hal-01927007v1
Deposit thumbnail

Variance-Aware Regret Bounds for Undiscounted Reinforcement Learning in MDPs

Mohammad Sadegh Talebi , Odalric-Ambrym Maillard

Journal of Machine Learning Research, 2018, pp.1-36

Article dans une revue hal-01737142v1
Deposit thumbnail

The Non-stationary Stochastic Multi-armed Bandit Problem

Robin Allesiardo , Raphaël Féraud , Odalric-Ambrym Maillard

International Journal of Data Science and Analytics, 2017, 3 (4), pp.267-283. ⟨10.1007/s41060-017-0050-5⟩

Article dans une revue hal-01575000v1
Deposit thumbnail

Concentration inequalities for sampling without replacement

Rémi Bardenet , Odalric-Ambrym Maillard

Bernoulli, 2015, 21 (3), pp.1361-1385. ⟨10.3150/14-BEJ605⟩

Article dans une revue hal-01216652v1
Deposit thumbnail

Latent Bandits

Odalric-Ambrym Maillard , Shie Mannor

JFPDA, 2014, pp.05

Article dans une revue hal-00990804v1
Deposit thumbnail

Sub-sampling for Multi-armed Bandits

Akram Baransi , Odalric-Ambrym Maillard , Shie Mannor

Proceedings of the European Conference on Machine Learning, 2014, pp.13

Article dans une revue hal-01025651v2
Deposit thumbnail

Kullback-Leibler Upper Confidence Bounds for Optimal Sequential Allocation

Olivier Cappé , Aurélien Garivier , Odalric-Ambrym Maillard , Rémi Munos , Gilles Stoltz

Annals of Statistics, 2013, 41 (3), pp.1516-1541. ⟨10.1214/13-AOS1119⟩

Article dans une revue hal-00738209v2
Deposit thumbnail

Hierarchical Subspaces of Policies for Continual Offline Reinforcement Learning

Anthony Kobanda , Rémy Portelas , Odalric-Ambrym Maillard , Ludovic Denoyer

MCDC Workshop at ICLR 2025, Apr 2025, Singapore, Singapore

Communication dans un congrès hal-05126349v1
Deposit thumbnail

A Continual Offline Reinforcement Learning Benchmark for Navigation Tasks

Anthony Kobanda , Odalric-Ambrym Maillard , Rémy Portelas

IEEE Conference on Games, Aug 2025, Lisboa, Portugal

Communication dans un congrès hal-05126447v1
Deposit thumbnail

Bandits with Multimodal Structure

Hassan Saber , Odalric-Ambrym Maillard

RLC 2024 - Reinforcement Learning Conference, Aug 2024, Amherst Massachusetts, United States. pp.39

Communication dans un congrès hal-04711994v1

CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption

Shubhada Agrawal , Timothée Mathieu , Debabrota Basu , Odalric-Ambrym Maillard

International Conference on Algorithmic Learning Theory (ALT), Feb 2024, San Diego (CA), United States. pp.74-124

Communication dans un congrès hal-04260464v1
Deposit thumbnail

Power Mean Estimation in Stochastic Monte-Carlo Tree Search

Tuan Quang Tuan Dam , Odalric-Ambrym Maillard , Emilie Kaufmann

Uncertainty in Artificial Intelligence, Jul 2024, Barcelona, Spain

Communication dans un congrès hal-04714124v1
Deposit thumbnail

Fast Asymptotically Optimal Algorithms for Non-Parametric Stochastic Bandits

Dorian Baudry , Fabien Pesquerel , Rémy Degenne , Odalric-Ambrym Maillard

NeurIPS 2023 - Thirty-seventh Conference on Neural Information Processing Systems, Dec 2023, New Orleans (Louisiana), United States

Communication dans un congrès hal-04337742v1
Deposit thumbnail

Farm-gym: A modular reinforcement learning platform for stochastic agronomic games

Odalric-Ambrym Maillard , Timothée Mathieu , Debabrota Basu

AIAFS 2023 - Artificial Intelligence for Agriculture and Food Systems, Feb 2023, Wahington DC, United States

Communication dans un congrès hal-03960683v1
Deposit thumbnail

Logarithmic regret in communicating MDPs: Leveraging known dynamics with bandits

Hassan Saber , Fabien Pesquerel , Odalric-Ambrym Maillard , Mohammad Sadegh Talebi

Asian Conference on Machine Learning, Nov 2023, Istanbul, Turkey

Communication dans un congrès hal-04241513v1
Deposit thumbnail

Risk-aware linear bandits with convex loss

Patrick Saux , Odalric-Ambrym Maillard

International Conference on Artificial Intelligence and Statistics (AISTATS), Apr 2023, Valencia, Spain

Communication dans un congrès hal-04044440v1
Deposit thumbnail

Learning crop management by reinforcement: gym-DSSAT

Romain Gautron , Emilio J Padrón , Philippe Preux , Julien Bigot , Odalric-Ambrym Maillard et al.

AIAFS 2023 - 2nd AAAI Workshop on AI for Agriculture and Food Systems, Feb 2023, Washignton DC, United States

Communication dans un congrès hal-03976393v1
Deposit thumbnail

Bregman Deviations of Generic Exponential Families

Sayak Ray Chowdhury , Patrick Saux , Odalric-Ambrym Maillard , Aditya Gopalan

Conference On Learning Theory (COLT), Jul 2023, Bangalore, India

Communication dans un congrès hal-04161043v1
Deposit thumbnail

Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration & Planning

Reda Ouhamma , Debabrota Basu , Odalric-Ambrym Maillard

Proceedings of the AAAI Conference on Artificial Intelligence, Feb 2023, Washignton DC, United States. pp.9336-9344, ⟨10.1609/aaai.v37i8.26119⟩

Communication dans un congrès hal-03790997v2
Deposit thumbnail

Risk-aware linear bandits with convex loss

Patrick Saux , Odalric-Ambrym Maillard

European Workshop on Reinforcement Learning, Sep 2022, Milan, Italy

Communication dans un congrès hal-03776680v1
Deposit thumbnail

IMED-RL: Regret optimal learning of ergodic Markov decision processes

Fabien Pesquerel , Odalric-Ambrym Maillard

NeurIPS 2022 - Thirty-sixth Conference on Neural Information Processing Systems, Nov 2022, New-Orleans, United States

Communication dans un congrès hal-03825423v1
Deposit thumbnail

Indexed Minimum Empirical Divergence for Unimodal Bandits

Hassan Saber , Pierre Ménard , Odalric-Ambrym Maillard

NeurIPS 2021 - International Conference on Neural Information Processing Systems, Dec 2021, Virtual-only Conference, United States

Communication dans un congrès hal-03446617v1
Deposit thumbnail

Learning Value Functions in Deep Policy Gradients using Residual Variance

Yannis Flet-Berliac , Reda Ouhamma , Odalric-Ambrym Maillard , Philippe Preux

ICLR 2021 - International Conference on Learning Representations, May 2021, Vienna / Virtual, Austria

Communication dans un congrès hal-02964174v3
Deposit thumbnail

From Optimality to Robustness: Dirichlet Sampling Strategies in Stochastic Bandits

Dorian Baudry , Patrick Saux , Odalric-Ambrym Maillard

NeurIPS 2021 - 35th International Conference on Neural Information Processing Systems, Dec 2021, Sydney, Australia

Communication dans un congrès hal-03421252v2
Deposit thumbnail

Routine Bandits: Minimizing Regret on Recurring Problems

Hassan Saber , Léo Saci , Odalric-Ambrym Maillard , Audrey Durand

ECML-PKDD 2021, Sep 2021, Bilbao, Spain

Communication dans un congrès hal-03286539v1
Deposit thumbnail

Improved Exploration in Factored Average-Reward MDPs

Sadegh Talebi , Anders Jonsson , Odalric-Ambrym Maillard

24th International Conference on Artificial Intelligence and Statistics, 2021, San diego (virtual), United States

Communication dans un congrès hal-03780564v1
Deposit thumbnail

Stochastic bandits with groups of similar arms

Fabien Pesquerel , Hassan Saber , Odalric-Ambrym Maillard

NeurIPS 2021 - Thirty-fifth Conference on Neural Information Processing Systems, Dec 2021, Sydney, Australia

Communication dans un congrès hal-03427597v1
Deposit thumbnail

Optimal Thompson Sampling strategies for support-aware CVaR bandits

Dorian Baudry , Romain Gautron , Emilie Kaufmann , Odalric-Ambrym Maillard

38th International Conference on Machine Learning, Jul 2021, Virtual, United States

Communication dans un congrès hal-03447244v1
Deposit thumbnail

Reinforcement Learning in Parametric MDPs with Exponential Families

Sayak Ray Chowdhury , Aditya Gopalan , Odalric-Ambrym Maillard

International Conference on Artificial Intelligence and Statistics, 2021, San diego, United States. pp.1855-1863

Communication dans un congrès hal-03472116v1
Deposit thumbnail

Robust-Adaptive Interval Predictive Control for Linear Uncertain Systems

Edouard Leurent , Denis Efimov , Odalric-Ambrym Maillard

CDC 2020 - 59th IEEE Conference on Decision and Control, Dec 2020, Jeju Island / Virtual, South Korea

Communication dans un congrès hal-02942414v1
Deposit thumbnail

Robust-Adaptive Control of Linear Systems: beyond Quadratic Costs

Edouard Leurent , Denis Efimov , Odalric-Ambrym Maillard

NeurIPS 2020 - 34th Conference on Neural Information Processing Systems, Dec 2020, Vancouver / Virtual, Canada

Communication dans un congrès hal-03004060v1
Deposit thumbnail

Tightening Exploration in Upper Confidence Reinforcement Learning

Hippolyte Bourel , Odalric-Ambrym Maillard , Mohammad Sadegh Talebi

International Conference on Machine Learning, Jul 2020, Vienna, Austria

Communication dans un congrès hal-03000664v1
Deposit thumbnail

Monte-Carlo Graph Search: the Value of Merging Similar States

Edouard Leurent , Odalric-Ambrym Maillard

ACML 2020 - 12th Asian Conference on Machine Learning, Nov 2020, Bangkok / Virtual, Thailand. pp.577 - 602

Communication dans un congrès hal-03004124v2
Deposit thumbnail

Sub-sampling for Efficient Non-Parametric Bandit Exploration

Dorian Baudry , Emilie Kaufmann , Odalric-Ambrym Maillard

NeurIPS 2020, Dec 2020, Vancouver, Canada

Communication dans un congrès hal-02977552v1
Deposit thumbnail

Restarted Bayesian Online Change-point Detector achieves Optimal Detection Delay

Réda Alami , Odalric-Ambrym Maillard , Raphael Féraud

International Conference on Machine Learning, Jul 2020, Wien, Austria

Communication dans un congrès hal-03021712v1
Deposit thumbnail

Model-Based Reinforcement Learning Exploiting State-Action Equivalence

Mahsa Asadi , Mohammad Sadegh Talebi , Hippolyte Bourel , Odalric-Ambrym Maillard

ACML 2019, Proceedings of Machine Learning Research, Nov 2019, Nagoya, Japan. pp.204 - 219

Communication dans un congrès hal-02378887v1
Deposit thumbnail

Practical Open-Loop Optimistic Planning

Edouard Leurent , Odalric-Ambrym Maillard

European Conference on Machine Learning, Sep 2019, Würzburg, Germany

Communication dans un congrès hal-02375697v1
Deposit thumbnail

Sequential change-point detection: Laplace concentration of scan statistics and non-asymptotic delay bounds

Odalric-Ambrym Maillard

Algorithmic Learning Theory, 2019, Chicago, United States. pp.1 - 23

Communication dans un congrès hal-02351665v1
Deposit thumbnail

Budgeted Reinforcement Learning in Continuous State Space

Nicolas Carrara , Edouard Leurent , Romain Laroche , Tanguy Urvoy , Odalric-Ambrym Maillard et al.

Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada

Communication dans un congrès hal-02375727v1
Deposit thumbnail

Learning Multiple Markov Chains via Adaptive Allocation

Mohammad Sadegh Talebi , Odalric-Ambrym Maillard

Advances in Neural Information Processing Systems 32 (NIPS 2019), Dec 2019, Vancouver, Canada

Communication dans un congrès hal-02387345v1
Deposit thumbnail

Regret Bounds for Learning State Representations in Reinforcement Learning

Ronald Ortner , Matteo Pirotta , Ronan Fruit , Alessandro Lazaric , Odalric-Ambrym Maillard

Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada

Communication dans un congrès hal-02375715v1
Deposit thumbnail

Approximate Robust Control of Uncertain Dynamical Systems

Edouard Leurent , Yann Blanco , Denis Efimov , Odalric-Ambrym Maillard

Proc. MLITS Workshop at NeurIPS, Dec 2018, Montreal, Canada

Communication dans un congrès hal-01931744v2
Deposit thumbnail

Efficient tracking of a growing number of experts

Jaouad Mourtada , Odalric-Ambrym Maillard

Algorithmic Learning Theory, Oct 2017, Tokyo, Japan. pp.1 - 23

Communication dans un congrès hal-01615424v1
Deposit thumbnail

Boundary Crossing for General Exponential Families

Odalric-Ambrym Maillard

Algorithmic Learning Theory, Oct 2017, Kyoto, Japan. pp.1 - 34

Communication dans un congrès hal-01615427v1
Deposit thumbnail

Spectral Learning from a Single Trajectory under Finite-State Policies

Borja Balle , Odalric-Ambrym Maillard

International conference on Machine Learning, Jul 2017, Sidney, France

Communication dans un congrès hal-01590940v1
Deposit thumbnail

Pliable rejection sampling

Akram Erraqabi , Michal Valko , Alexandra Carpentier , Odalric-Ambrym Maillard

International Conference on Machine Learning, Jun 2016, New York City, United States

Communication dans un congrès hal-01322168v1

Selecting Near-Optimal Approximate State Representations in Reinforcement Learning

Ronald Ortner , Odalric-Ambrym Maillard , Daniil Ryabko

International Conference on Algorithmic Learning Theory (ALT), Oct 2014, Bled, Slovenia. pp.140-154

Communication dans un congrès hal-01057562v1
Deposit thumbnail

Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning

Odalric-Ambrym Maillard , Phuong Nguyen , Ronald Ortner , Daniil Ryabko

ICML - 30th International Conference on Machine Learning, 2013, Atlanta, USA, United States. pp.543-551

Communication dans un congrès hal-00778586v1

Competing with an Infinite Set of Models in Reinforcement Learning

Phuong Nguyen , Odalric-Ambrym Maillard , Daniil Ryabko , Ronald Ortner

AISTATS, 2013, Arizona, United States. pp.463-471

Communication dans un congrès hal-00823230v1

Selecting the State-Representation in Reinforcement Learning

Odalric-Ambrym Maillard , Rémi Munos , Daniil Ryabko

Neural Information Processing Systems, Dec 2011, Granada, Spain

Communication dans un congrès hal-00639483v1
Deposit thumbnail

A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences

Odalric-Ambrym Maillard , Rémi Munos , Gilles Stoltz

24th Annual Conference on Learning Theory : COLT'11, Jul 2011, Budapest, Hungary. pp.18

Communication dans un congrès inria-00574987v2
Deposit thumbnail

Finite-Sample Analysis of Bellman Residual Minimization

Odalric-Ambrym Maillard , Rémi Munos , Alessandro Lazaric , Mohammad Ghavamzadeh

Asian Conference on Machine Learning, 2010, Japan

Communication dans un congrès hal-00830212v1
Deposit thumbnail

Compressed Least-Squares Regression

Odalric-Ambrym Maillard , Rémi Munos

NIPS 2009, Dec 2009, Vancouver, Canada

Communication dans un congrès inria-00419210v2
Deposit thumbnail

Adaptive Quasimetric Mapping : Principled Topological Abstraction for Robust Offline Goal-Conditioned Navigation

Anthony Kobanda , Waris Radji , Odalric-Ambrym Maillard , Rémy Portelas

2026

Pré-publication, Document de travail hal-05495482v2
Deposit thumbnail

The Regret Lower Bound for communicating Markov Decision Processes

Victor Boone , Odalric-Ambrym Maillard

2025

Pré-publication, Document de travail hal-05421579v1
Deposit thumbnail

Kriging and Gaussian Process Interpolation for Georeferenced Data Augmentation

Frédérick Fabre Ferber , Dominique Gay , Jean-Christophe Soulié , Jean Diatta , Odalric-Ambrym Maillard

2025

Pré-publication, Document de travail hal-04879232v1
Deposit thumbnail

How Hard is it to Confuse a World Model?

Waris Radji , Odalric-Ambrym Maillard

2025

Pré-publication, Document de travail hal-05326972v1
Deposit thumbnail

Bandits Corrupted by Nature: Lower Bounds on Regret and Robust Optimistic Algorithm

Debabrota Basu , Odalric-Ambrym Maillard , Timothée Mathieu

2022

Pré-publication, Document de travail hal-03611816v1
Deposit thumbnail

Optimal Strategies for Graph-Structured Bandits

Hassan Saber , Pierre Ménard , Odalric-Ambrym Maillard

2020

Pré-publication, Document de travail hal-02891139v2
Deposit thumbnail

Forced-exploration free Strategies for Unimodal Bandits

Hassan Saber , Pierre Ménard , Odalric-Ambrym Maillard

2020

Pré-publication, Document de travail hal-02883907v1
Deposit thumbnail

Active Roll-outs in MDP with Irreversible Dynamics

Odalric-Ambrym Maillard , Timothy Mann , Ronald Ortner , Shie Mannor

2019

Pré-publication, Document de travail hal-02177808v1
Deposit thumbnail

Upper Confidence Reinforcement Learning exploiting state-action equivalence

Odalric-Ambrym Maillard , Mahsa Asadi

2018

Pré-publication, Document de travail hal-01945034v1
Deposit thumbnail

Random Shuffling and Resets for the Non-stationary Stochastic Bandit Problem

Robin Allesiardo , Raphaël Féraud , Odalric-Ambrym Maillard

2016

Pré-publication, Document de travail hal-01400320v1
Deposit thumbnail

Self-normalization techniques for streaming confident regression

Odalric-Ambrym Maillard

2016

Pré-publication, Document de travail hal-01349727v2
Deposit thumbnail

Low-rank Bandits with Latent Mixtures

Aditya Gopalan , Odalric-Ambrym Maillard , Mohammadi Zaki

2016

Pré-publication, Document de travail hal-01400318v1
Deposit thumbnail

A note on replacing uniform subsampling by random projections in MCMC for linear regression of tall datasets

Rémi Bardenet , Odalric-Ambrym Maillard

2015

Pré-publication, Document de travail hal-01248841v1
Deposit thumbnail

Hierarchical Optimistic Region Selection driven by Curiosity

Odalric-Ambrym Maillard

2012

Pré-publication, Document de travail hal-00740418v1
Deposit thumbnail

Online allocation and homogeneous partitioning for piecewise constant mean-approximation

Odalric-Ambrym Maillard , Alexandra Carpentier

2012

Pré-publication, Document de travail hal-00742893v1
Deposit thumbnail

APPRENTISSAGE SÉQUENTIEL : Bandits, Statistique et Renforcement.

Odalric-Ambrym Maillard

Machine Learning [cs.LG]. Université des Sciences et Technologie de Lille - Lille I, 2011. English. ⟨NNT : ⟩

Thèse tel-00845410v1
Deposit thumbnail

Mathematics of Statistical Sequential Decision Making

Odalric-Ambrym Maillard

Mathematics [math]. Université de Lille, Sciences et Technologies, 2019

HDR tel-02162189v3