Publications

  • Scientific Productivity (updated December 2023): 41 publications, 51 co-authors according to Scopus
    • Peer-reviewed International Journal articles: 11 publications (4 as main contributor, 1 single-author), including JMLR (2), Machine Learning (2), RAS (1), ESWA (1), IEEE TNNLS (1), and IEEE T-ITS (1)
    • Peer-reviewed Intenrational Conference papers: 30 publications (11 as main contributor), including ICML (10), NeurIPS (8), AAAI (6), AISTATS (2), and UAI (1)
  • Publication Impact (updated December 2023): 713 citations and h-index 15 according to Google Scholar

 Google Scholar  ResearchGate ORCID dblp Scopus Semantic Scholar Publons

Books

  1. Alberto Maria Metelli. "Exploiting environment configurability in reinforcement learning ". Frontiers in Artificial Intelligence and Applications, 2022. [BibTeX] [Link]

Book Chapters

  1. Alberto Maria Metelli. "Configurable Environments in Reinforcement Learning: An Overview ". Special Topics in Information Technology, 2022. [BibTeX] [Link]

International Journal Articles

  1. Riccardo Poiani, Ciprian Stirbu, Alberto Maria Metelli, and Marcello Restelli. "Optimizing Empty Container Repositioning and Fleet Deployment via Configurable Semi-POMDPs ". IEEE Transactions on Intelligent Transportation Systems, 2023. SJR 2022: Q1 (Computer Science Applications). [BibTeX] [Link]
  2. Gianluca Drappo, Alberto Maria Metelli, and Marcello Restelli. "An Option-Dependent Analysis of Regret Minimization Algorithms in Finite-Horizon Semi-MDP ". Transactions on Machine Learning Research, 2023. [BibTeX] [Link]
  3. Filippo Fedeli, Alberto Maria Metelli, Francesco Trovò, and Marcello Restelli. "IWDA: Importance Weighting for Drift Adaptation in Streaming Supervised Learning Problems ". IEEE Transactions on Neural Networks and Learning Systems - Special Issue on Stream Learning, 2023. CORE 2020: A*. SJR 2022: Q1. [BibTeX] [Link]
  4. Marco Mussi, Davide Lombarda, Alberto Maria Metelli, Francesco Trovó, and Marcello Restelli. "ARLO: A framework for Automated Reinforcement Learning ". Expert Systems with Applications, 2023. CORE 2020: B. SJR 2022: Q1. [BibTeX] [Link]
  5. Alberto Maria Metelli. "A Unified View of Configurable Markov Decision Processes: Solution Concepts, Value Functions, and Operators ". Intelligenza Artificiale, 2022. (Invited publication as winner of the Premio Neodottori di Ricerca Marco Cadoli 2021). SJR 2022: Q3. [BibTeX] [Link]
  6. Alberto Maria Metelli, Guglielmo Manneschi, and Marcello Restelli. "Policy space identification in configurable environments ". Machine Learning, 2022. CORE 2020: A. SJR 2022: Q1. [BibTeX] [Link]
  7. Alberto Maria Metelli, Matteo Pirotta, Daniele Calandriello, and Marcello Restelli. "Safe Policy Iteration: A Monotonically Improving Approximate Policy Iteration Approach ". Journal of Machine Learning Research, 2021. CORE 2020: A*. SJR 2021: Q1. [BibTeX] [Link]
  8. Amarildo Likmeta, Alberto Maria Metelli, Giorgia Ramponi, Andrea Tirinzoni, Matteo Giuliani, and Marcello Restelli. "Dealing with multiple experts and non-stationarity in inverse reinforcement learning: an application to real-life problems ". Machine Learning, 2021. CORE 2020: A. SJR 2021: Q1. [BibTeX] [Link]
  9. Alberto Maria Metelli, Matteo Papini, Nico Montali, and Marcello Restelli. "Importance Sampling Techniques for Policy Optimization ". Journal of Machine Learning Research, 2020. CORE 2020: A*. SJR 2020: Q1. [BibTeX] [Link]
  10. Amarildo Likmeta, Alberto Maria Metelli, Andrea Tirinzoni, Riccardo Giol, Marcello Restelli, and Danilo Romano. "Combining reinforcement learning with rule-based controllers for transparent and general decision-making in autonomous driving ". Robotics and Autonomous Systems, 2020. CORE 2020: B. SJR 2020: Q1 (Computer Science Applications). [BibTeX] [Link]
  11. Alberto Maria Metelli, Matteo Pirotta, and Marcello Restelli. "On the use of the policy gradient and Hessian in inverse reinforcement learning ". Intelligenza Artificiale, 2020. (Invited publication as winner of the Premio NeoLaureati Leonardo Lesmo 2018). SJR 2020: Q3. [BibTeX] [Link]

International Conference Papers

  1. Riccardo Zamboni, Alberto Maria Metelli, and Marcello Restelli. "Distributional Policy Evaluation: a Maximum Entropy approach to Representation Learning ". Advances in Neural Information Processing Systems 36 (NeurIPS), 2023. Acceptance rate: 26.1%. CORE 2023: A*. GGS 2021: A++. [BibTeX] [Link]
  2. Riccardo Poiani, Alberto Maria Metelli, and Marcello Restelli. "Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach ". Advances in Neural Information Processing Systems 36 (NeurIPS), 2023. Acceptance rate: 26.1%. CORE 2023: A*. GGS 2021: A++. [BibTeX] [Link]
  3. Alberto Maria Metelli, Samuele Meta, and Marcello Restelli. "On the Relation between Policy Improvement and Off-Policy Minimum-Variance Policy Evaluation ". Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence (UAI), 2023. Acceptance rate: 243/778 (31.2%). CORE 2023: A. GGS 2021: A. [BibTeX] [Link]
  4. Alberto Maria Metelli, Filippo Lazzati, and Marcello Restelli. "Towards Theoretical Understanding of Inverse Reinforcement Learning ". Proceedings of the 40th International Conference on Machine Learning (ICML), 2023. Acceptance rate: 1827/6538 (27.9%), Oral: 156/6538 (2.39%). CORE 2023: A*. GGS 2021: A++. [BibTeX] [Link]
  5. Riccardo Poiani, Alberto Maria Metelli, and Marcello Restelli. "Truncating Trajectories in Monte Carlo Reinforcement Learning ". Proceedings of the 40th International Conference on Machine Learning (ICML), 2023. Acceptance rate: 1827/6538 (27.9%). CORE 2023: A*. GGS 2021: A++. [BibTeX] [Link]
  6. Marco Mussi, Alberto Maria Metelli, and Marcello Restelli. "Dynamical Linear Bandits ". Proceedings of the 40th International Conference on Machine Learning (ICML), 2023. Acceptance rate: 1827/6538 (27.9%). CORE 2023: A*. GGS 2021: A++. [BibTeX] [Link]
  7. Alberto Maria Metelli, Mirco Mutti, and Marcello Restelli. "A Tale of Sampling and Estimation in Discounted Reinforcement Learning ". Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, 2023. Acceptance rate: 496/1689 (29.3%), Notable paper (oral presentation): 32/1689 (1.9%). CORE 2023: A. GGS 2021: A+. [BibTeX] [Link]
  8. Eldowa Khaled Mazen Mahmoud Elsayed, Nicolò Cesa-Bianchi, Alberto Maria Metelli, and Marcello Restelli. "Bandits with Stochastic Experts: Towards Instance-Based Optimality ". 2023 IEEE Information Theory Workshop (ITW), 2023. CORE 2023: B. GGS 2021: B. [BibTeX]
  9. Davide Maran, Alberto Maria Metelli, and Marcello Restelli. "Tight Performance Guarantees of Imitator Policies with Continuous Actions ". The Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2023. Acceptance rate: 19.6%. CORE 2023: A*. GGS 2021: A++. [BibTeX] [Link]
  10. Amarildo Likmeta, Matteo Sacco, Alberto Maria Metelli, and Marcello Restelli. "Wasserstein Actor-Critic: Directed Exploration via Optimism for Continuous-Actions Control ". The Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2023. Acceptance rate: 19.6%. CORE 2023: A*. GGS 2021: A++. [BibTeX] [Link]
  11. Luca Sabbioni, Luca Al Daire, Lorenzo Bisi, Alberto Maria Metelli, and Marcello Restelli. "Simultaneously Updating All Persistence Values in Reinforcement Learning ". The Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2023. Acceptance rate: 19.6%. CORE 2023: A*. GGS 2021: A++. [BibTeX] [Link]
  12. Riccardo Poiani, Alberto Maria Metelli, and Marcello Restelli. "Multi-Fidelity Best-Arm Identification ". Advances in Neural Information Processing Systems 35 (NeurIPS), 2022. Acceptance rate: 2665/10411 (25.6%). CORE 2021: A*. GGS 2021: A++. [BibTeX] [Link]
  13. Alberto Maria Metelli, Matteo Pirola, Francesco Trovò, and Marcello Restelli. "Stochastic Rising Bandits ". Proceedings of the 39th International Conference on Machine Learning (ICML), 2022. Acceptance rate: 1235/5630 (21.9%). CORE 2021: A*. GGS 2021: A++. [BibTeX] [Link]
  14. Giorgio Manganini, Angelo Damiani, Alberto Maria Metelli, and Marcello Restelli. "Balancing Sample Efficiency and Suboptimality in Inverse Reinforcement Learning ". Proceedings of the 39th International Conference on Machine Learning (ICML), 2022. Acceptance rate: 1235/5630 (21.9%). CORE 2021: A*. GGS 2021: A++. [BibTeX] [Link]
  15. Julen Cestero, Marco Quartulli, Alberto Maria Metelli, and Marcello Restelli. "Storehouse: a Reinforcement Learning Environment for Optimizing Warehouse Management ". 2022 IEEE World Congress on Computational Intelligence - International Joint Conference on Neural Networks (IJCNN), 2022. CORE 2021: B. GGS 2021: A-. [BibTeX] [Link]
  16. Pierre Liotet, Francesco Vidaich, Alberto Maria Metelli, and Marcello Restelli. "Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization ". The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI), 2022. Acceptance rate: 1349/9020 (15.0%). CORE 2021: A*. GGS 2021: A++. [BibTeX] [Link]
  17. Alberto Maria Metelli, Alessio Russo, and Marcello Restelli. "Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and Learning ". Advances in Neural Information Processing Systems 34 (NeurIPS), 2021. Acceptance rate: 2344/9122 (25.7%), Spotlight: 260/9122 (2.9%). CORE 2021: A*. GGS 2021: A++. [BibTeX] [Link]
  18. Giorgia Ramponi, Alberto Maria Metelli, Alessandro Concetti, and Marcello Restelli. "Learning in Non-Cooperative Configurable Markov Decision Processes ". Advances in Neural Information Processing Systems 34 (NeurIPS), 2021. Acceptance rate: 2344/9122 (25.7%). CORE 2021: A*. GGS 2021: A++. [BibTeX] [Link]
  19. Alberto Maria Metelli*, Giorgia Ramponi*, Alessandro Concetti, and Marcello Restelli. "Provably Efficient Learning of Transferable Rewards ". Proceedings of the 38th International Conference on Machine Learning (ICML), 2021. Acceptance rate: 1184/5513 (21.5%). CORE 2021: A*. GGS 2021: A++. [BibTeX] [Link]
  20. Alberto Maria Metelli*, Matteo Papini*, Pierluca D'Oro, and Marcello Restelli. "Policy Optimization as Online Learning with Mediator Feedback ". The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021. Acceptance rate: 1692/7911 (21.4%). CORE 2021: A*. GGS 2021: A++. [BibTeX] [Link]
  21. Alberto Maria Metelli, Flavio Mazzolini, Lorenzo Bisi, Luca Sabbioni, and Marcello Restelli. "Control Frequency Adaptation via Action Persistence in Batch Reinforcement Learning ". Proceedings of the 37th International Conference on Machine Learning (ICML), 2020. Acceptance rate: 1088/4990 (21.8%). CORE 2020: A*. GGS 2018: A++. [BibTeX] [Link]
  22. Giorgia Ramponi, Amarildo Likmeta, Alberto Maria Metelli, Andrea Tirinzoni, and Marcello Restelli. "Truly Batch Model-Free Inverse Reinforcement Learning about Multiple Intentions ". Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (AISTATS), 2020. CORE 2020: A. GGS 2018: A+. [BibTeX] [Link]
  23. Pierluca D'Oro*, Alberto Maria Metelli*, Andrea Tirinzoni, Matteo Papini, and Marcello Restelli. "Gradient-Aware Model-Based Policy Search ". The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 2020. Acceptance rate: 1591/7737 (20.6%). CORE 2020: A*. GGS 2018: A++. [BibTeX] [Link]
  24. Alberto Maria Metelli*, Amarildo Likmeta*, and Marcello Restelli. "Propagating Uncertainty in Reinforcement Learning via Wasserstein Barycenters ". Advances in Neural Information Processing Systems 32 (NeurIPS), 2019. Acceptance rate: 428/6743 (21.2%). CORE 2018: A*. GGS 2018: A++. [BibTeX] [Link]
  25. Mario Beraha, Alberto Maria Metelli, Matteo Papini, Andrea Tirinzoni, and Marcello Restelli. "Feature Selection via Mutual Information: New Theoretical Insights ". International Joint Conference on Neural Networks (IJCNN), 2019. CORE 2018: A. GGS 2018: B. [BibTeX] [Link]
  26. Alberto Maria Metelli, Emanuele Ghelfi, and Marcello Restelli. "Reinforcement Learning in Configurable Continuous Environments ". Proceedings of the 36th International Conference on Machine Learning (ICML), 2019. Acceptance rate: 773/3424 (22.6%). CORE 2018: A*. GGS 2018: A++. [BibTeX] [Link]
  27. Matteo Papini, Alberto Maria Metelli, Lorenzo Lupo, and Marcello Restelli. "Optimistic Policy Optimization via Multiple Importance Sampling ". Proceedings of the 36th International Conference on Machine Learning (ICML), 2019. Acceptance rate: 773/3424 (22.6%). CORE 2018: A*. GGS 2018: A++. [BibTeX] [Link]
  28. Alberto Maria Metelli, Matteo Papini, Francesco Faccio, and Marcello Restelli. "Policy Optimization via Importance Sampling ". Advances in Neural Information Processing Systems 31 (NeurIPS), 2018. Acceptance rate: 1011/4856 (20.8%), Oral: 30/4856 (0.62%). CORE 2018: A*. GGS 2018: A++. [BibTeX] [Link]
  29. Alberto Maria Metelli*, Mirco Mutti*, and Marcello Restelli. "Configurable Markov Decision Processes ". Proceedings of the 35th International Conference on Machine Learning (ICML), 2018. Acceptance rate: 618/2473 (25.0%). CORE 2018: A*. GGS 2018: A++. [BibTeX] [Link]
  30. Alberto Maria Metelli, Matteo Pirotta, and Marcello Restelli. "Compatible Reward Inverse Reinforcement Learning ". Advances in Neural Information Processing Systems 30 (NIPS), 2017. Acceptance rate: 678/3240 (20.9%). CORE 2017: A*. GGS 2017: A++. [BibTeX] [Link]

International Workshop Papers

  1. Riccardo Poiani, Alberto Maria Metelli, and Marcello Restelli. "Pure Exploration under Mediatorstextquoteright Feedback ". NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World, 2023. [BibTeX] [Link]
  2. Gianmarco Genalti, Lupo Marsigli, Nicola Gatti, and Alberto Maria Metelli. "Towards Fully Adaptive Regret Minimization in Heavy-Tailed Bandits ". NeurIPS 2023 Workshop Heavy Tails in Machine Learning, 2023. [BibTeX] [Link]
  3. Alessio Russo, Alberto Maria Metelli, and Marcello Restelli. "Switching Latent Bandits ". Sixteenth European Workshop on Reinforcement Learning, 2023. [BibTeX] [Link]
  4. Filippo Lazzati, Alberto Maria Metelli, and Marcello Restelli. "On the Sample Complexity of Inverse Reinforcement Learning ". Sixteenth European Workshop on Reinforcement Learning, 2023. [BibTeX] [Link]
  5. Alessandro Montenegro, Marco Mussi, Francesco Trov{\`o}, Marcello Restelli, and Alberto Maria Metelli. "Stochastic Rising Bandits: A Best Arm Identification Approach ". Sixteenth European Workshop on Reinforcement Learning, 2023. [BibTeX] [Link]
  6. Riccardo Zamboni, Alberto Maria Metelli, and Marcello Restelli. "Distributional Policy Evaluation: a Maximum Entropy approach to Representation Learning ". Sixteenth European Workshop on Reinforcement Learning, 2023. [BibTeX] [Link]
  7. Francesco Bacchiocchi, Gianmarco Genalti, Davide Maran, Marco Mussi, Marcello Restelli, Nicola Gatti, and Alberto Maria Metelli. "Online Learning in Autoregressive Dynamics ". Sixteenth European Workshop on Reinforcement Learning, 2023. [BibTeX] [Link]
  8. Gianluca Drappo, Alberto Maria Metelli, and Marcello Restelli. "A Provably Efficient Option-Based Algorithm for both High-Level and Low-Level Learning ". Sixteenth European Workshop on Reinforcement Learning, 2023. [BibTeX] [Link]
  9. Riccardo Poiani, Nicole Nobili, Alberto Maria Metelli, and Marcello Restelli. "Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach ". Sixteenth European Workshop on Reinforcement Learning, 2023. [BibTeX] [Link]
  10. Th{\'e}o Vincent, Alberto Maria Metelli, Jan Peters, Marcello Restelli, and Carlo D'Eramo. "Parameterized projected Bellman operator ". ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems, 2023. [BibTeX] [Link]
  11. Alessandro Montenegro, Marco Mussi, Francesco Trov{\`o}, Marcello Restelli, and Alberto Maria Metelli. "A Best Arm Identification Approach for Stochastic Rising Bandits ". ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems, 2023. [BibTeX] [Link]
  12. Amarildo Likmeta, Matteo Sacco, Alberto Maria Metelli, and Marcello Restelli. "Directed Exploration via Uncertainty-Aware Critics ". Decision Awareness in Reinforcement Learning Workshop @ ICML 2022, 2022. [BibTeX] [Link]
  13. Alberto Maria Metelli, Samuele Meta, and Marcello Restelli. "Policy Optimization via Optimal Policy Evaluation ". Deep Reinforcement Learning Workshop - NeurIPS 2021, 2021. [BibTeX] [Link]
  14. Alberto Maria Metelli, Alessio Russo, and Marcello Restelli. "Subgaussian Importance Sampling for Off-Policy Evaluation and Learning ". ICML-21 Workshop on Reinforcement Learning Theory, 2021. [BibTeX] [Link]
  15. Giorgia Ramponi*, Alberto Maria Metelli*, and Marcello Restelli. "Efficient Inverse Reinforcement Learning of Transferable Rewards ". ICML-21 Workshop on Reinforcement Learning Theory, 2021. [BibTeX] [Link]
  16. Giorgia Ramponi, Alberto Maria Metelli, Alessandro Concetti, and Marcello Restelli. "Online Learning in Non-Cooperative Configurable Markov Decision Process ". AAAI-21 Workshop on Reinforcement Learning in Games, 2021. [BibTeX] [Link]
  17. Amarildo Likmeta, Alberto Maria Metelli, Giorgia Ramponi, Andrea Tirinzoni, Matteo Giuliani, and Marcello Restelli. "Handling Non-Stationary Experts in Inverse Reinforcement Learning: A Water System Control Case Study ". Challenges of Real-World RL Workshop @ NeurIPS 2020, 2020. [BibTeX] [Link]
  18. Amarildo Likmeta, Alberto Maria Metelli, Andrea Tirinzoni, Riccardo Giol, Marcello Restelli, Danilo Romano, and Andrea Alessandretti. "Autonomous Driving with Reinforcement Learning and Rule-based Policies ". Workshop on AI for Autonomous Driving (AIAD) @ICML 2020, 2020. [BibTeX] [Link]
  19. Pierluca D'Oro*, Alberto Maria Metelli*, Andrea Tirinzoni, Matteo Papini, and Marcello Restelli. "Gradient-Aware Model-based Policy Search ". Workshop on Meta-Learning (MetaLearn 2019) @NeurIPS 2019, 2019. [BibTeX] [Link]
  20. Alberto Maria Metelli*, Mirco Mutti*, and Marcello Restelli. "Configurable Markov Decision Processes ". European Workshop on Reinforcement Learning 14 (EWRL 14), 2018. [BibTeX] [Link]
  21. Mattia Bianchi, Federico Cesaro, Filippo Ciceri, Mattia Dagrada, Alberto Gasparin, Daniele Grattarola, Ilyas Inajjar, Alberto Maria Metelli, and Leonardo Cella. "Content-Based Approaches for Cold-Start Job Recommendations ". Proceedings of the Recommender Systems Challenge 2017, 2017. [BibTeX] [Link]

International Conference Abstracts

  1. Giorgio Manganini, Angelo Damiani, Alberto Maria Metelli, and Marcello Restelli. "A Novel Inverse Reinforcement Learning Formulation for Sample-Aware Forward Learning ". The Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM), 2022. [BibTeX]
  2. Luca Sabbioni, Luca Al Daire, Lorenzo Bisi, Alberto Maria Metelli, and Marcello Restelli. "All-persistence Bellman Update for Reinforcement Learning ". The Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM), 2022. [BibTeX]
  3. Matteo Giuliani, Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli, and Andrea Castelletti. "Advancing drought monitoring via feature extraction and multi-task learning algorithms ". EGU General Assembly 2022, 2022. [BibTeX] [Link]
  4. Verónica Torralba, Stefano Materia, Carmen Álvarez-Castro, Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli, and Silvio Gualdi. "Seasonal forecasts for hydropower: downscaling of precipitation in South American basins ". EGU General Assembly 2022, 2022. [BibTeX] [Link]
  5. Matteo Giuliani, Alberto Maria Metelli, Andrea Castelletti, and Marcello Restelli. "Advancing drought monitoring via feature extraction ". Earth and Space Science Open Archive, 2021. [BibTeX] [Link]

Theses

  1. Alberto Maria Metelli. "Exploiting Environment Configurability in Reinforcement Learning ". Politecnico di Milano, 2021. [BibTeX] [Link]
  2. Alberto Maria Metelli. "Compatible Reward Inverse Reinforcement Learning ". Politecnico di Milano, 2017. [BibTeX] [Link]