Marco Mussi

International Conferences

2026

1. Worst-Case Regret Bounds for Combinatorial Bandits with Ranking Feedback Cristiano Migali, Gianmarco Genalti, Alberto Maria Metelli and Marco Mussi NeurIPS 2026 To appear Link Paper Poster
2. Online Compatible Reward Identification from Preference Feedback Simone Drago, Marco Mussi and Alberto Maria Metelli ICML 2026 Link Paper Poster
3. Fast Mixing Steady-State Control in Markov Decision Processes Federico Corso, Marco Mussi and Alberto Maria Metelli ICML 2026 Link Paper Poster
4. Learning to Rank from Incomplete Rankings Cristiano Migali, Gianmarco Genalti, Alberto Maria Metelli and Marco Mussi ICML 2026 Link Paper Poster
5. Reusing Trajectories in Policy Gradients Enables Fast Convergence Alessandro Montenegro, Federico Mansutti, Marco Mussi, Matteo Papini and Alberto Maria Metelli ICML 2026 Link Paper arXiv Poster

2025

1. Tightening Regret Lower and Upper Bounds in Restless Rising Bandits Cristiano Migali, Marco Mussi, Gianmarco Genalti and Alberto Maria Metelli NeurIPS 2025 Link Paper Poster Slides
2. Sleeping Reinforcement Learning Simone Drago*, Marco Mussi* and Alberto Maria Metelli ICML 2025 Link Paper Poster
3. Towards Theoretical Understanding of Sequential Decision Making with Preference Feedback Simone Drago, Marco Mussi and Alberto Maria Metelli ICML 2025 Link Paper Poster
4. Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity Alessandro Montenegro, Marco Mussi, Matteo Papini and Alberto Maria Metelli ICML 2025 Link Paper Poster
5. Position: Constants are Critical in Regret Bounds for Reinforcement Learning Simone Drago, Marco Mussi and Alberto Maria Metelli ICML 2025 Link Paper Poster

2024

1. Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning Alessandro Montenegro, Marco Mussi, Matteo Papini and Alberto Maria Metelli NeurIPS 2024 Link Paper arXiv Poster Slides
2. Factored-Reward Bandits with Intermediate Observations Marco Mussi*, Simone Drago*, Marcello Restelli and Alberto Maria Metelli ICML 2024 Link Paper Poster Slides
3. Best Arm Identification for Stochastic Rising Bandits Marco Mussi, Alessandro Montenegro, Francesco Trovò, Marcello Restelli and Alberto Maria Metelli ICML 2024 Spotlight Link Paper arXiv Poster
4. Learning Optimal Deterministic Policies with Stochastic Policy Gradients Alessandro Montenegro, Marco Mussi, Alberto Maria Metelli and Matteo Papini ICML 2024 Spotlight Link Paper arXiv Poster
5. Graph-Triggered Rising Bandits Gianmarco Genalti, Marco Mussi, Nicola Gatti, Marcello Restelli, Matteo Castiglioni and Alberto Maria Metelli ICML 2024 Link Paper Poster
6. Autoregressive Bandits Francesco Bacchiocchi*, Gianmarco Genalti*, Davide Maran*, Marco Mussi*, Marcello Restelli, Nicola Gatti and Alberto Maria Metelli AISTATS 2024 Link Paper arXiv Poster Slides

2023

1. Dynamical Linear Bandits Marco Mussi, Alberto Maria Metelli and Marcello Restelli ICML 2023 Link Paper arXiv Poster Slides
2. Dynamic Pricing with Volume Discounts in Online Settings Marco Mussi*, Gianmarco Genalti*, Alessandro Nuara, Francesco Trovò, Marcello Restelli and Nicola Gatti IAAI 2023 Innovative Application of AI Award Link Paper arXiv Poster Slides Award

2022

1. Pricing the Long Tail by Explainable Product Aggregation and Monotonic Bandits Marco Mussi, Gianmarco Genalti, Francesco Trovò, Alessandro Nuara, Nicola Gatti and Marcello Restelli KDD 2022 Oral Link Paper Poster Slides

Journals

2026

1. Bridging Rested and Restless Bandits with Graph-Triggering: Rising and Rotting Gianmarco Genalti, Marco Mussi, Nicola Gatti, Marcello Restelli, Matteo Castiglioni and Alberto Maria Metelli Journal of Machine Learning Research, 2026 Link Paper arXiv
2. Trading-off Statistical and Computational Efficiency via W-step Markov Decision Processes: A Policy Gradient Approach Gianmarco Tedeschi, Marco Mussi, Alberto Maria Metelli and Marcello Restelli Machine Learning, 2026 Link Paper Poster Slides

2025

1. Human-AI Interaction in Safety-Critical Network Infrastructures Marco Mussi, Alberto Maria Metelli, Marcello Restelli, Gianvito Losapio, Ricardo Jorge Bessa, Daniel Boos, Clark Borst, Giulia Leto, Alberto Castagna, Ricardo Chavarriaga, Duarte Dias, Adrian Egli, Andrina Eisenegger, Yassine El Manyari, Anton Fuxjäger, Joaquim Geraldes, Samira Hamouche, Mohamed Hassouna, Bruno Lemetayer, Milad Leyli-Abadi, Roman Liessner, Jonas Lundberg, Antoine Marot, Maroua Meddeb, Viola Schiaffonati, Manuel Schneider, Thilo Stadelmann, Julia Usher, Herke van Hoof, Jan Viebahn, Toni Waefler and Giacomo Zanotti iScience, 2025 Link Paper
2. Factored-Reward Bandits with Intermediate Observations: Regret Minimization and Best Arm Identification Marco Mussi*, Simone Drago*, Marcello Restelli and Alberto Maria Metelli Artificial Intelligence, 2025 Link Paper
3. Generalizing the Regret: an Analysis of Lower and Upper Bounds Marco Mussi and Alberto Maria Metelli Journal of Artificial Intelligence Research, 2025 Link Paper

2024

1. A Reinforcement Learning Controller Optimizing Costs and Battery State of Health in Smart Grids Marco Mussi, Luigi Pellegrino, Oscar Francesco Pindaro, Marcello Restelli and Francesco Trovò Journal of Energy Storage, 2024 Link Paper

2023

1. ARLO: A Framework for Automated Reinforcement Learning Marco Mussi, Davide Lombarda, Alberto Maria Metelli, Francesco Trovò and Marcello Restelli Expert Systems with Applications, 2023 Link Paper arXiv

2022

1. An Online State of Health Estimation Method for Lithium-Ion Batteries based on Time Partitioning and Data-Driven Model Identification Marco Mussi, Luigi Pellegrino, Marcello Restelli and Francesco Trovò Journal of Energy Storage, 2022 Link Paper

2021

1. A voltage dynamic-based state of charge estimation method for batteries storage systems Marco Mussi, Luigi Pellegrino, Marcello Restelli and Francesco Trovò Journal of Energy Storage, 2021 Link Paper

Workshops

2026

1. Combinatorial Bandits with Plackett-Luce Feedback: A Worst-Case Analysis Cristiano Migali, Gianmarco Genalti, Alberto Maria Metelli and Marco Mussi EWRL 2026 Link Paper Poster
2. Variance-Aware Optimal Ranking in Log-Concave Random Utility Models Diego Alovisetti, Marco Mussi and Alberto Maria Metelli EWRL 2026 Link Paper Poster
3. Modeling Incomparability: A New Rationality Paradigm for Preference-Based Reinforcement Learning Simone Drago, Marco Mussi, Leonardo Bianconi and Alberto Maria Metelli ICML 2026 EIML Workshop Paper Poster
4. Robust Learning to Rank from Incomplete Rankings under Positional Censoring Cristiano Migali, Gianmarco Genalti, Alberto Maria Metelli and Marco Mussi ICML 2026 EIML Workshop Spotlight Paper Poster Slides

2025

1. Trading-off Reward Maximization and Stability in Sequential Decision Making Federico Corso, Marco Mussi and Alberto Maria Metelli EWRL 2025 Link Paper Poster
2. A Theoretical Perspective on Sequential Decision Making with Preference Feedback Simone Drago, Marco Mussi and Alberto Maria Metelli EWRL 2025 Link Paper Poster
3. A Novel Self-Normalized Bernstein-Like Dimension-Free Inequality and Regret Bounds for Generalized Kernelized Bandits Alberto Maria Metelli, Simone Drago and Marco Mussi EWRL 2025 Link Paper Poster
4. Gym4ReaL: A Benchmark Suite for Evaluating Reinforcement Learning in Realistic Domains Davide Salaorni, Vincenzo De Paola, Samuele Delpero, Giovanni Dispoto, Paolo Bonetti, Alessio Russo, Giuseppe Calcagno, Francesco Trovò, Matteo Papini, Alberto Maria Metelli, Marco Mussi and Marcello Restelli EWRL 2025 Link Paper Poster
5. Power Grid Control with Graph-Based Distributed Reinforcement Learning Carlo Fabrizio*, Gianvito Losapio*, Marco Mussi, Alberto Maria Metelli and Marcello Restelli ECML 2025 MLSPS Workshop Paper arXiv Poster

2024

1. State and Action Factorization in Power Grids Gianvito Losapio, Davide Beretta, Marco Mussi, Alberto Maria Metelli and Marcello Restelli ECML 2024 MLSPS Workshop Paper arXiv Poster Slides
2. Open Problem: Tight Bounds for Bernoulli Rewards in Kernelized Multi-Armed Bandits Simone Drago and Marco Mussi ICML 2024 ARLET Workshop Link Paper Poster
3. Intermediate Observations in Factored-Reward Bandits Simone Drago, Marco Mussi, Marcello Restelli and Alberto Maria Metelli AAMAS 2024 ALA Workshop Link Paper Slides

2023

1. Online Learning in Autoregressive Dynamics Francesco Bacchiocchi*, Gianmarco Genalti*, Davide Maran*, Marco Mussi*, Marcello Restelli, Nicola Gatti and Alberto Maria Metelli EWRL 2023 Link Paper Poster
2. Stochastic Rising Bandits: A Best Arm Identification Approach Alessandro Montenegro, Marco Mussi, Francesco Trovò, Marcello Restelli and Alberto Maria Metelli EWRL 2023 Link Paper Poster
3. A Best Arm Identification Approach for Stochastic Rising Bandits Alessandro Montenegro, Marco Mussi, Francesco Trovò, Marcello Restelli and Alberto Maria Metelli ICML 2023 F4LCD Workshop Link Paper Poster

2022

1. Dynamic Pricing with Online Data Aggregation and Learning Gianmarco Genalti, Marco Mussi, Alessandro Nuara and Nicola Gatti EWRL 2022 Oral Link Paper Poster Slides
2. Dynamical Linear Bandits for Long-Lasting Vanishing Rewards Marco Mussi, Alberto Maria Metelli and Marcello Restelli ICML 2022 CFOL Workshop Link Paper Poster

Book Chapters

2026

1. Multi-Armed Bandits Algorithms for Pricing and Advertising Marco Mussi Special Topics in Information Technology, 2026 Link Paper

Preprints

2026

1. Learning a Ranking from Human Feedback in Log-Concave Random Utility Models Diego Alovisetti, Marco Mussi and Alberto Maria Metelli arXiv:2610.07973 Paper arXiv
2. Reusing Past Samples in Proximal Policy Optimization: When and How Does It Help? Alessandro Montenegro, Riccardo Venturelli, Marco Mussi, Matteo Papini and Alberto Maria Metelli arXiv:2610.01399 Paper arXiv

2025

1. Online Dynamic Pricing of Complementary Products Marco Mussi and Marcello Restelli arXiv:2511.22291 Paper arXiv
2. Generalized Kernelized Bandits: A Novel Self-Normalized Bernstein-Like Dimension-Free Inequality and Regret Bounds Alberto Maria Metelli, Simone Drago and Marco Mussi arXiv:2508.01681 Paper arXiv
3. Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learning Davide Salaorni, Vincenzo De Paola, Samuele Delpero, Giovanni Dispoto, Paolo Bonetti, Alessio Russo, Giuseppe Calcagno, Francesco Trovò, Matteo Papini, Alberto Maria Metelli, Marco Mussi and Marcello Restelli arXiv:2507.00257 Paper arXiv
4. Learning Deterministic Policies with Policy Gradients in Constrained Markov Decision Processes Alessandro Montenegro, Leonardo Cesani, Marco Mussi, Matteo Papini and Alberto Maria Metelli arXiv:2506.05953 Paper arXiv
5. A refined Analysis of UCBVI Simone Drago, Marco Mussi and Alberto Maria Metelli arXiv:2502.17370 Paper arXiv

2024

1. Open Problem: Tight Bounds for Kernelized Multi-Armed Bandits with Bernoulli Rewards Marco Mussi, Simone Drago and Alberto Maria Metelli arXiv:2407.06321 Paper arXiv

Technical Reports

2024

1. Position paper on AI for the operation of critical energy and mobility network infrastructures Marco Mussi, Gianvito Losapio, Alberto Maria Metelli, Marcello Restelli, Ricardo Bessa, Antoine Marot, Daniel Boos, Clark Borst, Alberto Castagna, Duarte Dias, Adrian Egli, Andrina Eisenegger, Yassine El Manyari, Anton Fuxjäger, Samira Hamouche, Mohamed Hassouna, Bruno Lemetayer, Roman Liessner, Jonas Lundberg, Manuel Schneider, Irene Sturm, Julia Usher, Herke Van Hoof, Jan Viebahn and Toni Wäfler AI4REALNET, 2024 Link Report