Michal Valko

Most-cited papers

The Llama 3 Herd of Models
Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey +496 more
202420K citations
Semantic Scholar
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec +10 more
2020Neural Information Processing Systems9,284 citations
Semantic Scholar
A General Theoretical Paradigm to Understand Learning from Human Preferences
M. G. Azar, Mark Rowland, Bilal Piot, D. Guo +3 more
2023International Conference on Artificial Intelligence and Statistics1,172 citations
Semantic Scholar
Large-Scale Representation Learning on Graphs via Bootstrapping
S. Thakoor, Corentin Tallec, M. G. Azar, Mehdi Azabou +4 more
2021International Conference on Learning Representations353 citations
Semantic Scholar
Bootstrapped Representation Learning on Graphs
S. Thakoor, Corentin Tallec, M. G. Azar, Mehdi Azabou +4 more
2021arXiv.org336 citations
Semantic Scholar
Nash Learning from Human Feedback
Rémi Munos, Michal Valko, Daniele Calandriello, M. G. Azar +14 more
2023International Conference on Machine Learning261 citations
Semantic Scholar
Generalized Preference Optimization: A Unified Approach to Offline Alignment
Yunhao Tang, Z. Guo, Ze-Yu Zheng, Daniele Calandriello +6 more
2024International Conference on Machine Learning175 citations
Semantic Scholar
Broaden Your Views for Self-Supervised Video Learning
Adrià Recasens, Pauline Luc, Jean-Baptiste Alayrac, Luyu Wang +10 more
2021IEEE International Conference on Computer Vision146 citations Open access
Semantic Scholar
BYOL works even without batch statistics
Pierre H. Richemond, Jean-Bastien Grill, Florent Altché, Corentin Tallec +7 more
2020arXiv.org131 citations
Semantic Scholar
Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited
O. D. Domingues, Pierre M'enard, E. Kaufmann, Michal Valko
2020International Conference on Algorithmic Learning Theory124 citations
Semantic Scholar
Understanding the performance gap between online and offline alignment algorithms
Yunhao Tang, Z. Guo, Ze-Yu Zheng, Daniele Calandriello +7 more
2024arXiv.org119 citations
Semantic Scholar
Fast active learning for pure exploration in reinforcement learning
Pierre M'enard, O. D. Domingues, Anders Jonsson, E. Kaufmann +2 more
2020International Conference on Machine Learning117 citations
Semantic Scholar
Game Plan: What AI can do for Football, and What Football can do for AI
K. Tuyls, Shayegan Omidshafiei, Paul Muller, Zhe Wang +32 more
2020Journal of Artificial Intelligence Research115 citations
Semantic Scholar
BYOL-Explore: Exploration by Bootstrapped Prediction
Z. Guo, S. Thakoor, Mîruna Pislar, B. '. Pires +10 more
2022Neural Information Processing Systems108 citations Open access
Semantic Scholar
Human Alignment of Large Language Models through Online Preference Optimisation
Daniele Calandriello, D. Guo, Rémi Munos, Mark Rowland +9 more
2024International Conference on Machine Learning105 citations
Semantic Scholar
Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
A. Didolkar, Anirudh Goyal, N. Ke, Si-Yuan Guo +6 more
2024Neural Information Processing Systems103 citations
Semantic Scholar
Adaptive Reward-Free Exploration
E. Kaufmann, Pierre M'enard, O. D. Domingues, Anders Jonsson +2 more
2020International Conference on Algorithmic Learning Theory99 citations
Semantic Scholar
Monte-Carlo Tree Search as Regularized Policy Optimization
Jean-Bastien Grill, Florent Altché, Yun-Hao Tang, T. Hubert +3 more
2020International Conference on Machine Learning94 citations
Semantic Scholar
Gamification of Pure Exploration for Linear Bandits
Rémy Degenne, Pierre M'enard, Xuedong Shang, Michal Valko
2020International Conference on Machine Learning93 citations
Semantic Scholar
Retrieval-Augmented Reinforcement Learning
Anirudh Goyal, A. Friesen, Andrea Banino, T. Weber +12 more
2022International Conference on Machine Learning79 citations
Semantic Scholar
Decoding-time Realignment of Language Models
Tian-Lin Liu, Shangmin Guo, L. Bianco, Daniele Calandriello +6 more
2024International Conference on Machine Learning78 citations
Semantic Scholar
Understanding Self-Predictive Learning for Reinforcement Learning
Yun-Hao Tang, Z. Guo, Pierre H. Richemond, B. '. Pires +12 more
2022International Conference on Machine Learning62 citations Open access
Semantic Scholar
Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction
Mehdi Azabou, M. G. Azar, Ran Liu, Chi-Heng Lin +9 more
2021arXiv.org60 citations
Semantic Scholar
UCB Momentum Q-learning: Correcting the bias without forgetting
Pierre Ménard, O. D. Domingues, Xuedong Shang, Michal Valko
2021International Conference on Machine Learning55 citations
Semantic Scholar
Stochastic bandits with arm-dependent delays
Anne Gael Manegueu, Claire Vernade, A. Carpentier, Michal Valko
2020International Conference on Machine Learning52 citations
Semantic Scholar
Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity
Ran Liu, Mehdi Azabou, M. Dabagia, Chi-Heng Lin +4 more
2021bioRxiv49 citations Open access
Semantic Scholar
Statistical Efficiency of Thompson Sampling for Combinatorial Semi-Bandits
Pierre Perrault, Etienne Boursier, Michal Valko, Vianney Perchet
2020Neural Information Processing Systems47 citations
Semantic Scholar
Planning in Markov Decision Processes with Gap-Dependent Sample Complexity
Anders Jonsson, E. Kaufmann, Pierre M'enard, O. D. Domingues +2 more
2020Neural Information Processing Systems46 citations
Semantic Scholar
A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces
O. D. Domingues, Pierre M'enard, Matteo Pirotta, E. Kaufmann +1 more
2020International Conference on Artificial Intelligence and Statistics46 citations
Semantic Scholar
Fast Rates for Maximum Entropy Exploration
D. Tiapkin, D. Belomestny, Daniele Calandriello, É. Moulines +6 more
2023International Conference on Machine Learning41 citations Open access
Semantic Scholar
Bayesian Policy Gradient and Actor-Critic Algorithms
M. Ghavamzadeh, Yaakov Engel, Michal Valko
2026Journal of machine learning research40 citations
Semantic Scholar
Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret
Jean Tarbouriech, Runlong Zhou, S. Du, Matteo Pirotta +2 more
2021Neural Information Processing Systems40 citations
Semantic Scholar
Geometric Entropic Exploration
Z. Guo, M. G. Azar, Alaa Saade, S. Thakoor +6 more
2021arXiv.org39 citations
Semantic Scholar
Half-Hop: A graph upsampling approach for slowing down message passing
Mehdi Azabou, Venkataramana Ganesh, S. Thakoor, Chi-Heng Lin +5 more
2023International Conference on Machine Learning37 citations Open access
Semantic Scholar
A single algorithm for both restless and rested rotting bandits
Julien Seznec, Pierre Ménard, A. Lazaric, Michal Valko
2020International Conference on Artificial Intelligence and Statistics34 citations
Semantic Scholar
Kernel-Based Reinforcement Learning: A Finite-Time Analysis
O. D. Domingues, Pierre Ménard, Matteo Pirotta, E. Kaufmann +1 more
2020International Conference on Machine Learning30 citations
Semantic Scholar
Sampling from a k-DPP without looking at all items
Daniele Calandriello, Michal Derezinski, Michal Valko
2020Neural Information Processing Systems30 citations
Semantic Scholar
From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses
D. Tiapkin, D. Belomestny, É. Moulines, A. Naumov +4 more
2022International Conference on Machine Learning28 citations Open access
Semantic Scholar
Revisiting Peng's Q(λ) for Modern Reinforcement Learning
Tadashi Kozuno, Yun-Hao Tang, Mark Rowland, R. Munos +4 more
2021International Conference on Machine Learning26 citations
Semantic Scholar
Near-linear Time Gaussian Process Optimization with Adaptive Batching and Resparsification
Daniele Calandriello, Luigi Carratino, A. Lazaric, Michal Valko +1 more
2020International Conference on Machine Learning25 citations
Semantic Scholar
Optimal Design for Reward Modeling in RLHF
Antoine Scheid, Etienne Boursier, A. Durmus, Michael I. Jordan +3 more
2024arXiv.org23 citations
Semantic Scholar
Learning in two-player zero-sum partially observable Markov games with perfect recall
Tadashi Kozuno, Pierre Ménard, R. Munos, Michal Valko
2021Neural Information Processing Systems23 citations
Semantic Scholar
Supplementary material to “Online A-Optimal Design and Active Linear Regression”
X. Fontaine, Pierre Perrault, Michal Valko, Vianney Perchet
202123 citations
Semantic Scholar
Improved Sleeping Bandits with Stochastic Actions Sets and Adversarial Rewards
Aadirupa Saha, P. Gaillard, Michal Valko
2020International Conference on Machine Learning23 citations
Semantic Scholar
Regret Bounds for Kernel-Based Reinforcement Learning
O. D. Domingues, Pierre M'enard, Matteo Pirotta, E. Kaufmann +1 more
2020arXiv.org22 citations
Semantic Scholar
Preference Optimization with Multi-Sample Comparisons
Chao-Qi Wang, Zhuokai Zhao, Chen Zhu, Karthik Abinav Sankararaman +7 more
2024arXiv.org21 citations
Semantic Scholar
Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall
Tadashi Kozuno, Pierre M'enard, R. Munos, Michal Valko
2021arXiv.org21 citations
Semantic Scholar
Budgeted Online Influence Maximization
Pierre Perrault, Zheng Wen, Michal Valko, Jennifer Healey
2020International Conference on Machine Learning21 citations
Semantic Scholar
A Provably Efficient Sample Collection Strategy for Reinforcement Learning
Jean Tarbouriech, Matteo Pirotta, Michal Valko, A. Lazaric
2020Neural Information Processing Systems21 citations
Semantic Scholar
Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times
Daniele Calandriello, Luigi Carratino, A. Lazaric, Michal Valko +1 more
2022International Conference on Machine Learning20 citations
Semantic Scholar