← Authors

Alberto Maria Metelli

56 papers · 2017–2025 · 8 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (8) 🌈 Renaissance Researcher (5) 🐝 Cross-Pollinator (8) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (13) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸƒ Academic Marathon (8) 🏠 Conference Loyalist (21) 🀝 Dynamic Duo (42) πŸ”¬ Deep Specialist (24) 🧬 Topic Evolution πŸ† Keyword Champion (10) ❓ The Questioner πŸ—ƒοΈ Keyword Collector (176) πŸ’Ž Century Club (56) πŸ”₯ Unstoppable (9) ⚑ Prolific Year (10)

Conferences

ICML (21) NIPS (13) AAAI (8) AISTATS (6) COLT (3) JMLR (3) IJCAI (1) UAI (1)

Top co-authors

Marcello Restelli (42) Matteo Papini (12) Marco Mussi (11) Riccardo Poiani (5) Davide Maran (5) Alessandro Montenegro (4) Simone Drago (4) Filippo Lazzati (4) Mirco Mutti (4) Gianmarco Genalti (4)

Research topics

Reinforcement Learning (1)

Keywords

policy optimization (10) inverse reinforcement learning (9) reinforcement learning (8) importance sampling (7) reward function (7) online learning (6) regret bound (6) markov decision process (5) sample complexity (5) imitation learning (4) bandit algorithm (4) off-policy learning (4) multi-armed bandit (4) regret minimization (4) policy gradient (4) sequential decision-making (3) stochastic bandit (3) continuous control (3) wasserstein distance (3) best-arm identification (3)

Papers

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