Alessandro Lazaric

Temporal Difference Flows ICML 2025 Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models ICLR 2025 Fast Imitation via Behavior Foundation Models ICLR 2024 Simple Ingredients for Offline Reinforcement Learning ICML 2024 Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies ICLR 2023 Layered State Discovery for Incremental Autonomous Exploration ICML 2023 Contextual bandits with concave rewards, and an application to fair ranking ICLR 2023 On the Complexity of Representation Learning in Contextual Linear Bandits AISTATS 2023 Reaching Goals is Hard: Settling the Sample Complexity of the Stochastic Shortest Path ALT 2023 Temporal abstractions-augmented temporally contrastive learning: An alternative to the Laplacian in RL UAI 2022 Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning ICLR 2022 Top K Ranking for Multi-Armed Bandit with Noisy Evaluations AISTATS 2022 Adaptive Multi-Goal Exploration AISTATS 2022 Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees NIPS 2022 A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning ICLR 2022 A general sample complexity analysis of vanilla policy gradient AISTATS 2022 Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching ICLR 2022 Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times ICML 2022 Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping CORL 2022 Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection NIPS 2021 Reinforcement Learning with Prototypical Representations ICML 2021 Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model ALT 2021 Leveraging Good Representations in Linear Contextual Bandits ICML 2021 Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret NIPS 2021 A Provably Efficient Sample Collection Strategy for Reinforcement Learning NIPS 2021 Frequentist Regret Bounds for Randomized Least-Squares Value Iteration AISTATS 2020 A single algorithm for both restless and rested rotting bandits AISTATS 2020 Learning Near Optimal Policies with Low Inherent Bellman Error ICML 2020 No-Regret Exploration in Goal-Oriented Reinforcement Learning ICML 2020 Meta-learning with Stochastic Linear Bandits ICML 2020 Near-linear time Gaussian process optimization with adaptive batching and resparsification ICML 2020 Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation ICML 2020 Active Model Estimation in Markov Decision Processes UAI 2020 An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits NIPS 2020 Improved Sample Complexity for Incremental Autonomous Exploration in MDPs NIPS 2020 Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration NIPS 2020 Adversarial Attacks on Linear Contextual Bandits NIPS 2020 Improved Algorithms for Conservative Exploration in Bandits AAAI 2020 Conservative Exploration in Reinforcement Learning AISTATS 2020 A Novel Confidence-Based Algorithm for Structured Bandits AISTATS 2020 Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret COLT 2019 A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning NIPS 2019 Limiting Extrapolation in Linear Approximate Value Iteration NIPS 2019 Regret Bounds for Learning State Representations in Reinforcement Learning NIPS 2019 Exploration Bonus for Regret Minimization in Discrete and Continuous Average Reward MDPs NIPS 2019 Word-order Biases in Deep-agent Emergent Communication ACL 2019 Active Exploration in Markov Decision Processes AISTATS 2019 Rotting bandits are no harder than stochastic ones AISTATS 2019 Improved large-scale graph learning through ridge spectral sparsification ICML 2018 Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning ICML 2018 Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes NIPS 2018 Fighting Boredom in Recommender Systems with Linear Reinforcement Learning NIPS 2018 Improved Regret Bounds for Thompson Sampling in Linear Quadratic Control Problems ICML 2018 Trading off Rewards and Errors in Multi-Armed Bandits AISTATS 2017 Exploration-Exploitation in MDPs with Options AISTATS 2017 Linear Thompson Sampling Revisited AISTATS 2017 Efficient Second-Order Online Kernel Learning with Adaptive Embedding NIPS 2017 Regret Minimization in MDPs with Options without Prior Knowledge NIPS 2017 Active Learning for Accurate Estimation of Linear Models ICML 2017 Second-Order Kernel Online Convex Optimization with Adaptive Sketching ICML 2017 Distributed Adaptive Sampling for Kernel Matrix Approximation AISTATS 2017 Thompson Sampling for Linear-Quadratic Control Problems AISTATS 2017 Open Problem: Approximate Planning of POMDPs in the class of Memoryless Policies COLT 2016 Reinforcement Learning of POMDPs using Spectral Methods COLT 2016 Improved Learning Complexity in Combinatorial Pure Exploration Bandits AISTATS 2016 Analysis of Classification-based Policy Iteration Algorithms JMLR 2016 Direct Policy Iteration with Demonstrations IJCAI 2015 Maximum Entropy Semi-Supervised Inverse Reinforcement Learning IJCAI 2015 Exploiting easy data in online optimization NIPS 2014 Sparse Multi-Task Reinforcement Learning NIPS 2014 Best-Arm Identification in Linear Bandits NIPS 2014 Online Stochastic Optimization under Correlated Bandit Feedback ICML 2014 Sequential Transfer in Multi-armed Bandit with Finite Set of Models NIPS 2013 Risk-Aversion in Multi-armed Bandits NIPS 2012 Best Arm Identification: A Unified Approach to Fixed Budget and Fixed Confidence NIPS 2012 Finite-Sample Analysis of Least-Squares Policy Iteration JMLR 2012 Multi-Bandit Best Arm Identification NIPS 2011 Transfer from Multiple MDPs NIPS 2011 Finite-sample Analysis of Bellman Residual Minimization ACML 2010 LSTD with Random Projections NIPS 2010 Reinforcement Learning in Continuous Action Spaces through Sequential Monte Carlo Methods NIPS 2007