Odalric-Ambrym Maillard

110 papers A* 18A 5B 8C 5Journal 57Unranked 15

Year	Rank	Type	Title / Venue / Authors
2025	C	`conf`	A Continual Offline Reinforcement Learning Benchmark for Navigation Tasks. CoG Anthony Kobanda, Odalric-Ambrym Maillard, Rémy Portelas
2025	J	`jnl`	A Continual Offline Reinforcement Learning Benchmark for Navigation Tasks. CoRR Anthony Kobanda, Odalric-Ambrym Maillard, Rémy Portelas
2025	J	`jnl`	Asymptotically Optimal Problem-Dependent Bandit Policies for Transfer Learning. CoRR Adrien Prévost, Timothée Mathieu, Odalric-Ambrym Maillard
2025	J	`jnl`	How Hard is it to Confuse a World Model? CoRR Waris Radji, Odalric-Ambrym Maillard
2025	J	`jnl`	Interpolation pour l'augmentation de donnees : Application à la gestion des adventices de la canne a sucre a la Reunion. CoRR Frédérick Fabre Ferber, Dominique Gay, Jean-Christophe Soulié, Jean Diatta, Odalric-Ambrym Maillard
2025	J	`jnl`	Kriging and Gaussian Process Interpolation for Georeferenced Data Augmentation. CoRR Frédérick Fabre Ferber, Dominique Gay, Jean-Christophe Soulié, Jean Diatta, Odalric-Ambrym Maillard
2025	J	`jnl`	Leveraging priors on distribution functions for multi-arm bandits. CoRR Sumit Vashishtha, Odalric-Ambrym Maillard
2025	A*	`conf`	Monte-Carlo Tree Search with Uncertainty Propagation via Optimal Transport. ICML Tuan Dam, Pascal Stenger, Lukas Schneider, Joni Pajarinen, Carlo D'Eramo, Odalric-Ambrym Maillard
2025	J	`jnl`	Offline Goal-Conditioned Reinforcement Learning with Projective Quasimetric Planning. CoRR Anthony Kobanda, Waris Radji, Mathieu Petitbois, Odalric-Ambrym Maillard, Rémy Portelas
2025	J	`jnl`	The Confusing Instance Principle for Online Linear Quadratic Control. CoRR Waris Radji, Odalric-Ambrym Maillard
2025	J	`jnl`	The regret lower bound for communicating Markov Decision Processes. CoRR Victor Boone, Odalric-Ambrym Maillard
2024	J	`jnl`	AdaStop: adaptive statistical testing for sound comparisons of Deep RL agents. Trans. Mach. Learn. Res. Timothée Mathieu, Matheus Centa, Riccardo Della Vecchia, Hector Kohler, Alena Shilova, Odalric-Ambrym Maillard, Philippe Preux
2024	J	`jnl`	Bandits Corrupted by Nature: Lower Bounds on Regret and Robust Optimistic Algorithms. Trans. Mach. Learn. Res. Timothée Mathieu, Debabrota Basu, Odalric-Ambrym Maillard
2024	J	`jnl`	Bandits with Multimodal Structure. RLJ Hassan Saber, Odalric-Ambrym Maillard
2024	B	`conf`	CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption. ALT Shubhada Agrawal, Timothée Mathieu, Debabrota Basu, Odalric-Ambrym Maillard
2024	J	`jnl`	Hierarchical Subspaces of Policies for Continual Offline Reinforcement Learning. CoRR Anthony Kobanda, Rémy Portelas, Odalric-Ambrym Maillard, Ludovic Denoyer
2024	J	`jnl`	How to Shrink Confidence Sets for Many Equivalent Discrete Distributions? CoRR Odalric-Ambrym Maillard, Mohammad Sadegh Talebi
2024	A	`conf`	Power Mean Estimation in Stochastic Monte-Carlo Tree Search. UAI Tuan Dam, Odalric-Ambrym Maillard, Emilie Kaufmann
2024	J	`jnl`	Power Mean Estimation in Stochastic Monte-Carlo Tree_Search. CoRR Tuan Dam, Odalric-Ambrym Maillard, Emilie Kaufmann
2024	J	`jnl`	Provably Efficient Exploration in Reward Machines with Low Regret. CoRR Hippolyte Bourel, Anders Jonsson, Odalric-Ambrym Maillard, Chenxiao Ma, Mohammad Sadegh Talebi
2024	—	`conf`	Évaluation de critères de sélection de noyaux pour la régression Ridge à noyau dans un contexte de petits jeux de données. EGC Frédérick Fabre Ferber, Dominique Gay, Jean-Christophe Soulié, Jean Diatta, Odalric-Ambrym Maillard
2023	J	`jnl`	AdaStop: sequential testing for efficient and reliable comparisons of Deep RL Agents. CoRR Timothée Mathieu, Riccardo Della Vecchia, Alena Shilova, Matheus Centa de Medeiros, Hector Kohler, Odalric-Ambrym Maillard, Philippe Preux
2023	J	`jnl`	CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption. CoRR Shubhada Agrawal, Timothée Mathieu, Debabrota Basu, Odalric-Ambrym Maillard
2023	A	`conf`	Exploration in Reward Machines with Low Regret. AISTATS Hippolyte Bourel, Anders Jonsson, Odalric-Ambrym Maillard, Mohammad Sadegh Talebi
2023	A*	`conf`	Fast Asymptotically Optimal Algorithms for Non-Parametric Stochastic Bandits. NeurIPS Dorian Baudry, Fabien Pesquerel, Rémy Degenne, Odalric-Ambrym Maillard
2023	C	`conf`	Logarithmic regret in communicating MDPs: Leveraging known dynamics with bandits. ACML Hassan Saber, Fabien Pesquerel, Odalric-Ambrym Maillard, Mohammad Sadegh Talebi
2023	J	`jnl`	Monte-Carlo tree search with uncertainty propagation via optimal transport. CoRR Tuan Dam, Pascal Stenger, Lukas Schneider, Joni Pajarinen, Carlo D'Eramo, Odalric-Ambrym Maillard
2022	J	`jnl`	A channel selection game for multi-operator LoRaWAN deployments. Comput. Networks Kinda Khawam, Hassan Fawaz, Samer Lahoud, Odalric-Ambrym Maillard, Steven Martin
2022	J	`jnl`	Bandits Corrupted by Nature: Lower Bounds on Regret and Robust Optimistic Algorithm. CoRR Debabrota Basu, Odalric-Ambrym Maillard, Timothée Mathieu
2022	J	`jnl`	Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration and Planning. CoRR Reda Ouhamma, Debabrota Basu, Odalric-Ambrym Maillard
2022	J	`jnl`	Bregman Deviations of Generic Exponential Families. CoRR Sayak Ray Chowdhury, Patrick Saux, Odalric-Ambrym Maillard, Aditya Gopalan
2022	J	`jnl`	Collaborative Algorithms for Online Personalized Mean Estimation. CoRR Mahsa Asadi, Aurélien Bellet, Odalric-Ambrym Maillard, Marc Tommasi
2022	J	`jnl`	Collaborative Algorithms for Online Personalized Mean Estimation. Trans. Mach. Learn. Res. Mahsa Asadi, Aurélien Bellet, Odalric-Ambrym Maillard, Marc Tommasi
2022	J	`jnl`	Efficient Change-Point Detection for Tackling Piecewise-Stationary Bandits. J. Mach. Learn. Res. Lilian Besson, Emilie Kaufmann, Odalric-Ambrym Maillard, Julien Seznec
2022	A*	`conf`	IMED-RL: Regret optimal learning of ergodic Markov decision processes. NeurIPS Fabien Pesquerel, Odalric-Ambrym Maillard
2022	J	`jnl`	Reinforcement learning for crop management support: Review, prospects and challenges. Comput. Electron. Agric. Romain Gautron, Odalric-Ambrym Maillard, Philippe Preux, Marc Corbeels, Régis Sabbadin
2022	J	`jnl`	Risk-aware linear bandits with convex loss. CoRR Patrick Saux, Odalric-Ambrym Maillard
2022	J	`jnl`	gym-DSSAT: a crop model turned into a Reinforcement Learning environment. CoRR Romain Gautron, Emilio J. Padrón, Philippe Preux, Julien Bigot, Odalric-Ambrym Maillard, David Emukpere
2021	A*	`conf`	From Optimality to Robustness: Adaptive Re-Sampling Strategies in Stochastic Bandits. NeurIPS Dorian Baudry, Patrick Saux, Odalric-Ambrym Maillard
2021	J	`jnl`	From Optimality to Robustness: Dirichlet Sampling Strategies in Stochastic Bandits. CoRR Dorian Baudry, Patrick Saux, Odalric-Ambrym Maillard
2021	A*	`conf`	Indexed Minimum Empirical Divergence for Unimodal Bandits. NeurIPS Hassan Saber, Pierre Ménard, Odalric-Ambrym Maillard
2021	J	`jnl`	Indexed Minimum Empirical Divergence for Unimodal Bandits. CoRR Hassan Saber, Pierre Ménard, Odalric-Ambrym Maillard
2021	A*	`conf`	Learning Value Functions in Deep Policy Gradients using Residual Variance. ICLR Yannis Flet-Berliac, Reda Ouhamma, Odalric-Ambrym Maillard, Philippe Preux
2021	A*	`conf`	Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits. NeurIPS Reda Ouhamma, Odalric-Ambrym Maillard, Vianney Perchet
2021	A	`conf`	Reinforcement Learning in Parametric MDPs with Exponential Families. AISTATS Sayak Ray Chowdhury, Aditya Gopalan, Odalric-Ambrym Maillard
2021	—	`conf`	Routine Bandits: Minimizing Regret on Recurring Problems. ECML/PKDD (1) Hassan Saber, Léo Saci, Odalric-Ambrym Maillard, Audrey Durand
2021	A*	`conf`	Stochastic Online Linear Regression: the Forward Algorithm to Replace Ridge. NeurIPS Reda Ouhamma, Odalric-Ambrym Maillard, Vianney Perchet
2021	A*	`conf`	Stochastic bandits with groups of similar arms. NeurIPS Fabien Pesquerel, Hassan Saber, Odalric-Ambrym Maillard
2020	J	`jnl`	Forced-exploration free Strategies for Unimodal Bandits. CoRR Hassan Saber, Pierre Ménard, Odalric-Ambrym Maillard
2020	J	`jnl`	Improved Exploration in Factored Average-Reward MDPs. CoRR Mohammad Sadegh Talebi, Anders Jonsson, Odalric-Ambrym Maillard
2020	J	`jnl`	Is Standard Deviation the New Standard? Revisiting the Critic in Deep Policy Gradients. CoRR Yannis Flet-Berliac, Reda Ouhamma, Odalric-Ambrym Maillard, Philippe Preux
2020	C	`conf`	Monte-Carlo Graph Search: the Value of Merging Similar States. ACML Edouard Leurent, Odalric-Ambrym Maillard
2020	J	`jnl`	Optimal Strategies for Graph-Structured Bandits. CoRR Hassan Saber, Pierre Ménard, Odalric-Ambrym Maillard
2020	J	`jnl`	Robust Estimation, Prediction and Control with Linear Dynamics and Generic Costs. CoRR Edouard Leurent, Denis V. Efimov, Odalric-Ambrym Maillard
2020	A*	`conf`	Robust-Adaptive Control of Linear Systems: beyond Quadratic Costs. NeurIPS Edouard Leurent, Odalric-Ambrym Maillard, Denis V. Efimov
2020	—	`conf`	Robust-Adaptive Interval Predictive Control for Linear Uncertain Systems. CDC Edouard Leurent, Denis V. Efimov, Odalric-Ambrym Maillard
2020	J	`jnl`	Robust-Adaptive Interval Predictive Control for Linear Uncertain Systems. CoRR Edouard Leurent, Denis V. Efimov, Odalric-Ambrym Maillard
2020	A*	`conf`	Sub-sampling for Efficient Non-Parametric Bandit Exploration. NeurIPS Dorian Baudry, Emilie Kaufmann, Odalric-Ambrym Maillard
2020	J	`jnl`	Sub-sampling for Efficient Non-Parametric Bandit Exploration. CoRR Dorian Baudry, Emilie Kaufmann, Odalric-Ambrym Maillard
2020	J	`jnl`	Thompson Sampling for CVaR Bandits. CoRR Dorian Baudry, Romain Gautron, Emilie Kaufmann, Odalric-Ambrym Maillard
2020	J	`jnl`	Tightening Exploration in Upper Confidence Reinforcement Learning. CoRR Hippolyte Bourel, Odalric-Ambrym Maillard, Mohammad Sadegh Talebi
2019	J	`jnl`	Approximate Robust Control of Uncertain Dynamical Systems. CoRR Edouard Leurent, Yann Blanco, Denis V. Efimov, Odalric-Ambrym Maillard
2019	A*	`conf`	Budgeted Reinforcement Learning in Continuous State Space. NeurIPS Nicolas Carrara, Edouard Leurent, Romain Laroche, Tanguy Urvoy, Odalric-Ambrym Maillard, Olivier Pietquin
2019	J	`jnl`	Distribution-dependent and Time-uniform Bounds for Piecewise i.i.d Bandits. CoRR Subhojyoti Mukherjee, Odalric-Ambrym Maillard
2019	A*	`conf`	Learning Multiple Markov Chains via Adaptive Allocation. NeurIPS Mohammad Sadegh Talebi, Odalric-Ambrym Maillard
2019	J	`jnl`	Learning Multiple Markov Chains via Adaptive Allocation. CoRR M. Sadegh Talebi, Odalric-Ambrym Maillard
2019	—	`book`	Mathematics of Statistical Sequential Decision Making. (Mathématique de la prise de décision séquentielle statistique). Odalric-Ambrym Maillard
2019	C	`conf`	Model-Based Reinforcement Learning Exploiting State-Action Equivalence. ACML Mahsa Asadi, Mohammad Sadegh Talebi, Hippolyte Bourel, Odalric-Ambrym Maillard
2019	J	`jnl`	Model-Based Reinforcement Learning Exploiting State-Action Equivalence. CoRR Mahsa Asadi, Mohammad Sadegh Talebi, Hippolyte Bourel, Odalric-Ambrym Maillard
2019	—	`conf`	Practical Open-Loop Optimistic Planning. ECML/PKDD (3) Edouard Leurent, Odalric-Ambrym Maillard
2019	J	`jnl`	Practical Open-Loop Optimistic Planning. CoRR Edouard Leurent, Odalric-Ambrym Maillard
2019	A*	`conf`	Regret Bounds for Learning State Representations in Reinforcement Learning. NeurIPS Ronald Ortner, Matteo Pirotta, Alessandro Lazaric, Ronan Fruit, Odalric-Ambrym Maillard
2019	J	`jnl`	Scaling up budgeted reinforcement learning. CoRR Nicolas Carrara, Edouard Leurent, Romain Laroche, Tanguy Urvoy, Odalric-Ambrym Maillard, Olivier Pietquin
2019	B	`conf`	Sequential change-point detection: Laplace concentration of scan statistics and non-asymptotic delay bounds. ALT Odalric-Ambrym Maillard
2018	J	`jnl`	Streaming kernel regression with provably adaptive mean, variance, and regularization. J. Mach. Learn. Res. Audrey Durand, Odalric-Ambrym Maillard, Joelle Pineau
2018	B	`conf`	Variance-Aware Regret Bounds for Undiscounted Reinforcement Learning in MDPs. ALT Mohammad Sadegh Talebi, Odalric-Ambrym Maillard
2018	J	`jnl`	Variance-Aware Regret Bounds for Undiscounted Reinforcement Learning in MDPs. CoRR Mohammad Sadegh Talebi, Odalric-Ambrym Maillard
2017	B	`conf`	Boundary Crossing for General Exponential Families. ALT Odalric-Ambrym Maillard
2017	B	`conf`	Efficient tracking of a growing number of experts. ALT Jaouad Mourtada, Odalric-Ambrym Maillard
2017	J	`jnl`	Efficient tracking of a growing number of experts. CoRR Jaouad Mourtada, Odalric-Ambrym Maillard
2017	A*	`conf`	Spectral Learning from a Single Trajectory under Finite-State Policies. ICML Borja Balle, Odalric-Ambrym Maillard
2017	J	`jnl`	Streaming kernel regression with provably adaptive mean, variance, and regularization. CoRR Audrey Durand, Odalric-Ambrym Maillard, Joelle Pineau
2017	J	`jnl`	The non-stationary stochastic multi-armed bandit problem. Int. J. Data Sci. Anal. Robin Allesiardo, Raphaël Féraud, Odalric-Ambrym Maillard
2016	J	`jnl`	Low-rank Bandits with Latent Mixtures. CoRR Aditya Gopalan, Odalric-Ambrym Maillard, Mohammadi Zaki
2016	A*	`conf`	Pliable Rejection Sampling. ICML Akram Erraqabi, Michal Valko, Alexandra Carpentier, Odalric-Ambrym Maillard
2016	J	`jnl`	Random Shuffling and Resets for the Non-stationary Stochastic Bandit Problem. CoRR Robin Allesiardo, Raphaël Féraud, Odalric-Ambrym Maillard
2014	—	`conf`	How hard is my MDP?" The distribution-norm to the rescue". NIPS Odalric-Ambrym Maillard, Timothy A. Mann, Shie Mannor
2014	A*	`conf`	Latent Bandits. ICML Odalric-Ambrym Maillard, Shie Mannor
2014	B	`conf`	Selecting Near-Optimal Approximate State Representations in Reinforcement Learning. ALT Ronald Ortner, Odalric-Ambrym Maillard, Daniil Ryabko
2014	J	`jnl`	Selecting Near-Optimal Approximate State Representations in Reinforcement Learning. CoRR Ronald Ortner, Odalric-Ambrym Maillard, Daniil Ryabko
2014	—	`conf`	Sub-sampling for Multi-armed Bandits. ECML/PKDD (1) Akram Baransi, Odalric-Ambrym Maillard, Shie Mannor
2013	A	`conf`	Competing with an Infinite Set of Models in Reinforcement Learning. AISTATS Phuong Nguyen, Odalric-Ambrym Maillard, Daniil Ryabko, Ronald Ortner
2013	J	`jnl`	Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning CoRR Odalric-Ambrym Maillard, Phuong Nguyen, Ronald Ortner, Daniil Ryabko
2013	—	`conf`	Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning. ICML (1) Odalric-Ambrym Maillard, Phuong Nguyen, Ronald Ortner, Daniil Ryabko
2013	B	`conf`	Robust Risk-Averse Stochastic Multi-armed Bandits. ALT Odalric-Ambrym Maillard
2013	J	`jnl`	Selecting the State-Representation in Reinforcement Learning CoRR Odalric-Ambrym Maillard, Rémi Munos, Daniil Ryabko
2012	—	`conf`	Hierarchical Optimistic Region Selection driven by Curiosity. NIPS Odalric-Ambrym Maillard
2012	J	`jnl`	Linear regression with random projections. J. Mach. Learn. Res. Odalric-Ambrym Maillard, Rémi Munos
2012	—	`conf`	Online allocation and homogeneous partitioning for piecewise constant mean-approximation. NIPS Alexandra Carpentier, Odalric-Ambrym Maillard
2011	—	`—`	(APPRENTISSAGE SÉQUENTIEL : Bandits, Statistique et Renforcement. Odalric-Ambrym Maillard
2011	A*	`conf`	A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences. COLT Odalric-Ambrym Maillard, Rémi Munos, Gilles Stoltz
2011	A	`conf`	Adaptive Bandits: Towards the best history-dependent strategy. AISTATS Odalric-Ambrym Maillard, Rémi Munos
2011	—	`conf`	Selecting the State-Representation in Reinforcement Learning. NIPS Odalric-Ambrym Maillard, Rémi Munos, Daniil Ryabko
2011	—	`conf`	Sparse Recovery with Brownian Sensing. NIPS Alexandra Carpentier, Odalric-Ambrym Maillard, Rémi Munos
2010	C	`conf`	Finite-sample Analysis of Bellman Residual Minimization. ACML Odalric-Ambrym Maillard, Rémi Munos, Alessandro Lazaric, Mohammad Ghavamzadeh
2010	—	`conf`	LSTD with Random Projections. NIPS Mohammad Ghavamzadeh, Alessandro Lazaric, Odalric-Ambrym Maillard, Rémi Munos
2010	—	`conf`	Online Learning in Adversarial Lipschitz Environments. ECML/PKDD (2) Odalric-Ambrym Maillard, Rémi Munos
2010	—	`conf`	Scrambled Objects for Least-Squares Regression. NIPS Odalric-Ambrym Maillard, Rémi Munos
2009	B	`conf`	Complexity versus Agreement for Many Views. ALT Odalric-Ambrym Maillard, Nicolas Vayatis
2009	—	`conf`	Compressed Least-Squares Regression. NIPS Odalric-Ambrym Maillard, Rémi Munos