Alberto Maria Metelli

Achieving Õ(√T) Regret in Average-Reward POMDPs with Known Observation Models AISTATS 2025 Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity ICML 2025 Efficient Exploitation of Hierarchical Structure in Sparse Reward Reinforcement Learning AISTATS 2025 Learning Utilities from Demonstrations in Markov Decision Processes ICML 2025 Open Problem: Regret Minimization in Heavy-Tailed Bandits with Unknown Distributional Parameters COLT 2025 Position: Constants are Critical in Regret Bounds for Reinforcement Learning ICML 2025 Sleeping Reinforcement Learning ICML 2025 Towards Theoretical Understanding of Sequential Decision Making with Preference Feedback ICML 2025 Autoregressive Bandits AISTATS 2024 Best Arm Identification for Stochastic Rising Bandits ICML 2024 Dissimilarity Bandits AISTATS 2024 Factored-Reward Bandits with Intermediate Observations ICML 2024 Graph-Triggered Rising Bandits ICML 2024 How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach NeurIPS 2024 Information Capacity Regret Bounds for Bandits with Mediator Feedback JMLR 2024 Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning NeurIPS 2024 Learning Optimal Deterministic Policies with Stochastic Policy Gradients ICML 2024 Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs NeurIPS 2024 No-Regret Reinforcement Learning in Smooth MDPs ICML 2024 Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms ICML 2024 Online Learning with Off-Policy Feedback in Adversarial MDPs IJCAI 2024 Optimal Multi-Fidelity Best-Arm Identification NeurIPS 2024 Parameterized Projected Bellman Operator AAAI 2024 Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs COLT 2024 Recent Advancements in Inverse Reinforcement Learning AAAI 2024 Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning NeurIPS 2024 (ε, u)-Adaptive Regret Minimization in Heavy-Tailed Bandits COLT 2024 A Tale of Sampling and Estimation in Discounted Reinforcement Learning AISTATS 2023 Distributional Policy Evaluation: a Maximum Entropy approach to Representation Learning NeurIPS 2023 Dynamical Linear Bandits ICML 2023 On the Relation between Policy Improvement and Off-Policy Minimum-Variance Policy Evaluation UAI 2023 Simultaneously Updating All Persistence Values in Reinforcement Learning AAAI 2023 Tight Performance Guarantees of Imitator Policies with Continuous Actions AAAI 2023 Towards Theoretical Understanding of Inverse Reinforcement Learning ICML 2023 Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach NeurIPS 2023 Truncating Trajectories in Monte Carlo Reinforcement Learning ICML 2023 Wasserstein Actor-Critic: Directed Exploration via Optimism for Continuous-Actions Control AAAI 2023 Balancing Sample Efficiency and Suboptimality in Inverse Reinforcement Learning ICML 2022 Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization AAAI 2022 Multi-Fidelity Best-Arm Identification NeurIPS 2022 Stochastic Rising Bandits ICML 2022 Learning in Non-Cooperative Configurable Markov Decision Processes NeurIPS 2021 Policy Optimization as Online Learning with Mediator Feedback AAAI 2021 Provably Efficient Learning of Transferable Rewards ICML 2021 Safe Policy Iteration: A Monotonically Improving Approximate Policy Iteration Approach JMLR 2021 Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and Learning NeurIPS 2021 Control Frequency Adaptation via Action Persistence in Batch Reinforcement Learning ICML 2020 Gradient-Aware Model-Based Policy Search AAAI 2020 Importance Sampling Techniques for Policy Optimization JMLR 2020 Truly Batch Model-Free Inverse Reinforcement Learning about Multiple Intentions AISTATS 2020 Optimistic Policy Optimization via Multiple Importance Sampling ICML 2019 Propagating Uncertainty in Reinforcement Learning via Wasserstein Barycenters NeurIPS 2019 Reinforcement Learning in Configurable Continuous Environments ICML 2019 Configurable Markov Decision Processes ICML 2018 Policy Optimization via Importance Sampling NeurIPS 2018 Compatible Reward Inverse Reinforcement Learning NeurIPS 2017