Odalric-Ambrym Maillard
Publications
Publications
|
|
Hierarchical Subspaces of Policies for Continual Offline Reinforcement LearningMCDC Workshop at ICLR 2025, Apr 2025, Singapore, Singapore |
|
|
A Continual Offline Reinforcement Learning Benchmark for Navigation TasksIEEE Conference on Games, Aug 2025, Lisboa, Portugal |
|
|
Bandits with Multimodal StructureRLC 2024 - Reinforcement Learning Conference, Aug 2024, Amherst Massachusetts, United States. pp.39 |
|
|
CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic CorruptionInternational Conference on Algorithmic Learning Theory (ALT), Feb 2024, San Diego (CA), United States. pp.74-124 |
|
|
Power Mean Estimation in Stochastic Monte-Carlo Tree SearchUncertainty in Artificial Intelligence, Jul 2024, Barcelona, Spain |
|
|
Fast Asymptotically Optimal Algorithms for Non-Parametric Stochastic BanditsNeurIPS 2023 - Thirty-seventh Conference on Neural Information Processing Systems, Dec 2023, New Orleans (Louisiana), United States |
|
|
Farm-gym: A modular reinforcement learning platform for stochastic agronomic gamesAIAFS 2023 - Artificial Intelligence for Agriculture and Food Systems, Feb 2023, Wahington DC, United States |
|
|
Logarithmic regret in communicating MDPs: Leveraging known dynamics with banditsAsian Conference on Machine Learning, Nov 2023, Istanbul, Turkey |
|
|
Risk-aware linear bandits with convex lossInternational Conference on Artificial Intelligence and Statistics (AISTATS), Apr 2023, Valencia, Spain |
|
|
Learning crop management by reinforcement: gym-DSSATAIAFS 2023 - 2nd AAAI Workshop on AI for Agriculture and Food Systems, Feb 2023, Washignton DC, United States |
|
|
Bregman Deviations of Generic Exponential FamiliesConference On Learning Theory (COLT), Jul 2023, Bangalore, India |
|
|
Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration & PlanningProceedings of the AAAI Conference on Artificial Intelligence, Feb 2023, Washignton DC, United States. pp.9336-9344, ⟨10.1609/aaai.v37i8.26119⟩ |
|
|
Risk-aware linear bandits with convex lossEuropean Workshop on Reinforcement Learning, Sep 2022, Milan, Italy |
|
|
IMED-RL: Regret optimal learning of ergodic Markov decision processesNeurIPS 2022 - Thirty-sixth Conference on Neural Information Processing Systems, Nov 2022, New-Orleans, United States |
|
|
Indexed Minimum Empirical Divergence for Unimodal BanditsNeurIPS 2021 - International Conference on Neural Information Processing Systems, Dec 2021, Virtual-only Conference, United States |
|
|
Learning Value Functions in Deep Policy Gradients using Residual VarianceICLR 2021 - International Conference on Learning Representations, May 2021, Vienna / Virtual, Austria |
|
|
From Optimality to Robustness: Dirichlet Sampling Strategies in Stochastic BanditsNeurIPS 2021 - 35th International Conference on Neural Information Processing Systems, Dec 2021, Sydney, Australia |
|
|
Routine Bandits: Minimizing Regret on Recurring ProblemsECML-PKDD 2021, Sep 2021, Bilbao, Spain |
|
|
Improved Exploration in Factored Average-Reward MDPs24th International Conference on Artificial Intelligence and Statistics, 2021, San diego (virtual), United States |
|
|
Stochastic bandits with groups of similar armsNeurIPS 2021 - Thirty-fifth Conference on Neural Information Processing Systems, Dec 2021, Sydney, Australia |
|
|
Optimal Thompson Sampling strategies for support-aware CVaR bandits38th International Conference on Machine Learning, Jul 2021, Virtual, United States |
|
|
Reinforcement Learning in Parametric MDPs with Exponential FamiliesInternational Conference on Artificial Intelligence and Statistics, 2021, San diego, United States. pp.1855-1863 |
|
|
Robust-Adaptive Interval Predictive Control for Linear Uncertain SystemsCDC 2020 - 59th IEEE Conference on Decision and Control, Dec 2020, Jeju Island / Virtual, South Korea |
|
|
Robust-Adaptive Control of Linear Systems: beyond Quadratic CostsNeurIPS 2020 - 34th Conference on Neural Information Processing Systems, Dec 2020, Vancouver / Virtual, Canada |
|
|
Tightening Exploration in Upper Confidence Reinforcement LearningInternational Conference on Machine Learning, Jul 2020, Vienna, Austria |
|
|
Monte-Carlo Graph Search: the Value of Merging Similar StatesACML 2020 - 12th Asian Conference on Machine Learning, Nov 2020, Bangkok / Virtual, Thailand. pp.577 - 602 |
|
|
Sub-sampling for Efficient Non-Parametric Bandit ExplorationNeurIPS 2020, Dec 2020, Vancouver, Canada |
|
|
Restarted Bayesian Online Change-point Detector achieves Optimal Detection DelayInternational Conference on Machine Learning, Jul 2020, Wien, Austria |
|
|
Model-Based Reinforcement Learning Exploiting State-Action EquivalenceACML 2019, Proceedings of Machine Learning Research, Nov 2019, Nagoya, Japan. pp.204 - 219 |
|
|
Practical Open-Loop Optimistic PlanningEuropean Conference on Machine Learning, Sep 2019, Würzburg, Germany |
|
|
Sequential change-point detection: Laplace concentration of scan statistics and non-asymptotic delay boundsAlgorithmic Learning Theory, 2019, Chicago, United States. pp.1 - 23 |
|
|
Budgeted Reinforcement Learning in Continuous State SpaceConference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada |
|
|
Learning Multiple Markov Chains via Adaptive AllocationAdvances in Neural Information Processing Systems 32 (NIPS 2019), Dec 2019, Vancouver, Canada |
|
|
Regret Bounds for Learning State Representations in Reinforcement LearningConference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada |
|
|
Approximate Robust Control of Uncertain Dynamical SystemsProc. MLITS Workshop at NeurIPS, Dec 2018, Montreal, Canada |
|
|
Efficient tracking of a growing number of expertsAlgorithmic Learning Theory, Oct 2017, Tokyo, Japan. pp.1 - 23 |
|
|
Boundary Crossing for General Exponential FamiliesAlgorithmic Learning Theory, Oct 2017, Kyoto, Japan. pp.1 - 34 |
|
|
Spectral Learning from a Single Trajectory under Finite-State PoliciesInternational conference on Machine Learning, Jul 2017, Sidney, France |
|
|
Pliable rejection samplingInternational Conference on Machine Learning, Jun 2016, New York City, United States |
Selecting Near-Optimal Approximate State Representations in Reinforcement LearningInternational Conference on Algorithmic Learning Theory (ALT), Oct 2014, Bled, Slovenia. pp.140-154 |
|
|
|
Optimal Regret Bounds for Selecting the State Representation in Reinforcement LearningICML - 30th International Conference on Machine Learning, 2013, Atlanta, USA, United States. pp.543-551 |
Competing with an Infinite Set of Models in Reinforcement LearningAISTATS, 2013, Arizona, United States. pp.463-471 |
|
Selecting the State-Representation in Reinforcement LearningNeural Information Processing Systems, Dec 2011, Granada, Spain |
|
|
|
A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences24th Annual Conference on Learning Theory : COLT'11, Jul 2011, Budapest, Hungary. pp.18 |
|
|
Finite-Sample Analysis of Bellman Residual MinimizationAsian Conference on Machine Learning, 2010, Japan |
|
|
Compressed Least-Squares RegressionNIPS 2009, Dec 2009, Vancouver, Canada |
|
|
Évaluation de critères de sélection de noyaux pour la régression Ridge à noyau dans un contexte de petits jeux de données24ème conférence francophone sur l'Extraction et la Gestion des Connaissances EGC 2024, Jan 2024, Dijon, France. RNTI E-40 |
|
|
Petits jeux de données et prédiction en Intelligence Artificielle, vers une meilleure cohabitation : Application à la gestion durable de l'enherbement des systèmes agricoles à La RéunionComité scientifique et technique du DPP CapTerre, Nov 2022, Saint-Gilles, La Réunion |
|
|
Memory Bandits: Towards the Switching Bandit Problem Best ResolutionMLSS 2018 - Machine Learning Summer School, Aug 2018, Madrid, Spain |
|
|
Latent Bandits.2014 |
|
|
Robust Risk-averse Stochastic Multi-Armed Bandits2013 |
|
|
gym-DSSAT: a crop model turned into a Reinforcement Learning environment[Research Report] RR-9460, Inria Lille. 2022, pp.31 |
|
|
Adaptive Bandits: Towards the best history-dependent strategy[Technical Report] 2011, pp.14 |
|
|
Linear regression with random projections[Technical Report] 2010, pp.22 |
|
|
Brownian Motions and Scrambled Wavelets for Least-Squares Regression[Technical Report] 2010, pp.13 |
|
|
APPRENTISSAGE SÉQUENTIEL : Bandits, Statistique et Renforcement.Machine Learning [cs.LG]. Université des Sciences et Technologie de Lille - Lille I, 2011. English. ⟨NNT : ⟩ |
|
|
Mathematics of Statistical Sequential Decision MakingMathematics [math]. Université de Lille, Sciences et Technologies, 2019 |
|
|
Basic Concentration Properties of Real-Valued DistributionsDoctoral. France. 2017 |