Publications

2025

Online learning in sequential Bayesian persuasion: Handling unknown priors. Martino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti, Francesco Trovò. Artif. Intell. (2025)
The evolutionary dynamics of soft-max policy gradient in multi-agent settings. Martino Bernasconi, Federico Cacciamani, Simone Fioravanti, Nicola Gatti, Francesco Trovò. Theor. Comput. Sci. (2025)

2024

No-Regret Reinforcement Learning in Smooth MDPs. Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restelli. ICML (2024)
Causal Feature Selection via Transfer Entropy. Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli. IJCNN (2024)
Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning. Alessandro Montenegro, Marco Mussi, Matteo Papini, Alberto Maria Metelli. NeurIPS (2024)
Factored-Reward Bandits with Intermediate Observations. Marco Mussi, Simone Drago, Marcello Restelli, Alberto Maria Metelli. ICML (2024)
Online Learning with Off-Policy Feedback in Adversarial MDPs. Francesco Bacchiocchi, Francesco Emanuele Stradi, Matteo Papini, Alberto Maria Metelli, Nicola Gatti. IJCAI (2024)
Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms. Filippo Lazzati, Mirco Mutti, Alberto Maria Metelli. ICML (2024)
Policy Gradient with Active Importance Sampling. Matteo Papini, Giorgio Manganini, Alberto Maria Metelli, Marcello Restelli. RLJ (2024)
Offline Primal-Dual Reinforcement Learning for Linear MDPs. Germano Gabbianelli, Gergely Neu, Matteo Papini, Nneka Okolo. AISTATS (2024)
Importance-Weighted Offline Learning Done Right. Germano Gabbianelli, Gergely Neu, Matteo Papini. ALT (2024)
Prediction of Kellgren-Lawrence Grade of Knee Osteoarthritis by Deep Residual Networks Using MR Image with Segmented Image and Slice Position. Daniele Manfredonia, Seiichi Harata, Takuto Sakuma, Francesco Trovò, Shohei Kato. ICAART (2024)
Recent Advancements in Inverse Reinforcement Learning. Alberto Maria Metelli. AAAI (2024)
How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach. Filippo Lazzati, Mirco Mutti, Alberto Maria Metelli. NeurIPS (2024)
A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics. Puze Liu, Jonas Günster, Niklas Funk, Simon Gröger, Dong Chen, Haitham Bou-Ammar, Julius Jankowski, Ante Maric, Sylvain Calinon, Andrej Orsula, Miguel S. Olivares-Méndez, Hongyi Zhou, Rudolf Lioutikov, Gerhard Neumann, Amarildo Likmeta, Amirhossein Zhalehmehrabi, Thomas Bonenfant, Marcello Restelli, Davide Tateo, Ziyuan Liu, Jan R. Peters. NeurIPS (2024)
Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs. Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restelli. COLT (2024)
How to Explore with Belief: State Entropy Maximization in POMDPs. Riccardo Zamboni, Duilio Cirino, Marcello Restelli, Mirco Mutti. ICML (2024)
Autoregressive Bandits. Francesco Bacchiocchi, Gianmarco Genalti, Davide Maran, Marco Mussi, Marcello Restelli, Nicola Gatti, Alberto Maria Metelli. AISTATS (2024)
Interpetable Target-Feature Aggregation for Multi-task Learning Based on Bias-Variance Analysis. Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli. ECML/PKDD (2024)
Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning. Mirco Mutti, Riccardo De Santi, Marcello Restelli, Alexander Marx, Giorgia Ramponi. ICLR (2024)
(ε, u)-Adaptive Regret Minimization in Heavy-Tailed Bandits. Gianmarco Genalti, Lupo Marsigli, Nicola Gatti, Alberto Maria Metelli. COLT (2024)
Online Markov Decision Processes Configuration with Continuous Decision Space. Davide Maran, Pierriccardo Olivieri, Francesco Emanuele Stradi, Giuseppe Urso, Nicola Gatti, Marcello Restelli. AAAI (2024)
Optimistic Information Directed Sampling. Gergely Neu, Matteo Papini, Ludovic Schwartz. COLT (2024)
Dissimilarity Bandits. Paolo Battellani, Alberto Maria Metelli, Francesco Trovò. AISTATS (2024)
Evolving Fuzzy Prediction Intervals in Nonstationary Environments. Oscar Cartagena, Francesco Trovò, Manuel Roveri, Doris Sáez. IEEE Trans. Emerg. Top. Comput. Intell. (2024)
Best Arm Identification for Stochastic Rising Bandits. Marco Mussi, Alessandro Montenegro, Francesco Trovò, Marcello Restelli, Alberto Maria Metelli. ICML (2024)
A multivariate approach for fuzzy prediction interval design and its application for a climatization system forecasting. Oscar Cartagena, Francesco Trovò, Doris Sáez. Expert Syst. Appl. (2024)
Optimizing Empty Container Repositioning and Fleet Deployment via Configurable Semi-POMDPs. Riccardo Poiani, Ciprian Stirbu, Alberto Maria Metelli, Marcello Restelli. IEEE Trans. Intell. Transp. Syst. (2024)
Transfer Learning for Dynamical Systems Models via Autoencoders and GANs. Angelo Damiani, Gustavo Viera-López, Giorgio Manganini, Alberto Maria Metelli, Marcello Restelli. ACC (2024)
Optimal Multi-Fidelity Best-Arm Identification. Riccardo Poiani, Rémy Degenne, Emilie Kaufmann, Alberto Maria Metelli, Marcello Restelli. NeurIPS (2024)
Adapting bandit algorithms for settings with sequentially available arms. Marco Gabrielli, Manuela Antonelli, Francesco Trovò. Eng. Appl. Artif. Intell. (2024)
The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough. Riccardo Zamboni, Duilio Cirino, Marcello Restelli, Mirco Mutti. RLJ (2024)
Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds. Gabor Paczolay, Matteo Papini, Alberto Maria Metelli, István Á. Harmati, Marcello Restelli. Mach. Learn. (2024)
Learning Extensive-Form Perfect Equilibria in Two-Player Zero-Sum Sequential Games. Martino Bernasconi, Alberto Marchesi, Francesco Trovò. AISTATS (2024)
Building Surrogate Models Using Trajectories of Agents Trained by Reinforcement Learning. Julen Cestero, Marco Quartulli, Marcello Restelli. ICANN (2024)
Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning. Riccardo Poiani, Gabriele Curti, Alberto Maria Metelli, Marcello Restelli. NeurIPS (2024)
A Provably Efficient Option-Based Algorithm for both High-Level and Low-Level Learning. Gianluca Drappo, Alberto Maria Metelli, Marcello Restelli. RLJ (2024)
Bandits with Ranking Feedback. Davide Maran, Francesco Bacchiocchi, Francesco Emanuele Stradi, Matteo Castiglioni, Nicola Gatti, Marcello Restelli. NeurIPS (2024)
Interpretable linear dimensionality reduction based on bias-variance analysis. Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli. Data Min. Knowl. Discov. (2024)
Graph-Triggered Rising Bandits. Gianmarco Genalti, Marco Mussi, Nicola Gatti, Marcello Restelli, Matteo Castiglioni, Alberto Maria Metelli. ICML (2024)
Parameterized Projected Bellman Operator. Théo Vincent, Alberto Maria Metelli, Boris Belousov, Jan Peters, Marcello Restelli, Carlo D'Eramo. AAAI (2024)
Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs. Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restelli. NeurIPS (2024)
The Power of Hybrid Learning in Industrial Robotics: Efficient Grasping Strategies with Supervised-Driven Reinforcement Learning. Vincenzo De Paola, Giuseppe Calcagno, Alberto Maria Metelli, Marcello Restelli. IJCNN (2024)
Learning Optimal Deterministic Policies with Stochastic Policy Gradients. Alessandro Montenegro, Marco Mussi, Alberto Maria Metelli, Matteo Papini. ICML (2024)

2023

Towards Theoretical Understanding of Inverse Reinforcement Learning. Alberto Maria Metelli, Filippo Lazzati, Marcello Restelli. ICML (2023)
Optimal Rates and Efficient Algorithms for Online Bayesian Persuasion. Martino Bernasconi, Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Francesco Trovò, Nicola Gatti. ICML (2023)
Truncating Trajectories in Monte Carlo Reinforcement Learning. Riccardo Poiani, Alberto Maria Metelli, Marcello Restelli. ICML (2023)
Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach. Riccardo Poiani, Nicole Nobili, Alberto Maria Metelli, Marcello Restelli. NeurIPS (2023)
A Tale of Sampling and Estimation in Discounted Reinforcement Learning. Alberto Maria Metelli, Mirco Mutti, Marcello Restelli. AISTATS (2023)
Stepsize Learning for Policy Gradient Methods in Contextual Markov Decision Processes. Luca Sabbioni, Francesco Corda, Marcello Restelli. ECML/PKDD (2023)
Dynamical Linear Bandits. Marco Mussi, Alberto Maria Metelli, Marcello Restelli. ICML (2023)
Information-Theoretic Regret Bounds for Bandits with Fixed Expert Advice. Khaled Eldowa, Nicolò Cesa-Bianchi, Alberto Maria Metelli, Marcello Restelli. ITW (2023)
Online Learning with Off-Policy Feedback. Germano Gabbianelli, Gergely Neu, Matteo Papini. ALT (2023)
On the Relation between Policy Improvement and Off-Policy Minimum-Variance Policy Evaluation. Alberto Maria Metelli, Samuele Meta, Marcello Restelli. UAI (2023)
Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization. Mirco Mutti, Riccardo De Santi, Emanuele Rossi, Juan Felipe Calderón, Michael M. Bronstein, Marcello Restelli. AAAI (2023)
Advancing Fraud Detection Systems Through Online Learning. Tommaso Paladini, Martino Bernasconi de Luca, Michele Carminati, Mario Polino, Francesco Trovò, Stefano Zanero. ECML/PKDD (2023)
Dynamic Pricing with Volume Discounts in Online Settings. Marco Mussi, Gianmarco Genalti, Alessandro Nuara, Francesco Trovò, Marcello Restelli, Nicola Gatti. AAAI (2023)
Tight Performance Guarantees of Imitator Policies with Continuous Actions. Davide Maran, Alberto Maria Metelli, Marcello Restelli. AAAI (2023)
Distributional Policy Evaluation: a Maximum Entropy approach to Representation Learning. Riccardo Zamboni, Alberto Maria Metelli, Marcello Restelli. NeurIPS (2023)
A Brief Guide to Multi-Objective Reinforcement Learning and Planning. Conor F. Hayes, Roxana Radulescu, Eugenio Bargiacchi, Johan Källström, Matthew Macfarlane, Mathieu Reymond, Timothy Verstraeten, Luisa M. Zintgraf, Richard Dazeley, Fredrik Heintz, Enda Howley, Athirai A. Irissappane, Patrick Mannion, Ann Nowé, Gabriel de Oliveira Ramos, Marcello Restelli, Peter Vamplew, Diederik M. Roijers. AAMAS (2023)
Constrained Phi-Equilibria. Martino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Francesco Trovò, Nicola Gatti. ICML (2023)
MetaLung: Towards a Secure Architecture for Lung Cancer Patient Care on the Metaverse. Michele Zanitti, Mieszko Ferens, Alberto Ferrarin, Francesco Trovò, Vanja Miskovic, Arsela Prelaj, Ming Shen, Sokol Kosta. MetaCom (2023)
Convex Reinforcement Learning in Finite Trials. Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, Marcello Restelli. J. Mach. Learn. Res. (2023)
An Option-Dependent Analysis of Regret Minimization Algorithms in Finite-Horizon Semi-MDP. Gianluca Drappo, Alberto Maria Metelli, Marcello Restelli. Trans. Mach. Learn. Res. (2023)
Risk-averse optimization of reward-based coherent risk measures. Massimiliano Bonetti, Lorenzo Bisi, Marcello Restelli. Artif. Intell. (2023)
IWDA: Importance Weighting for Drift Adaptation in Streaming Supervised Learning Problems. Filippo Fedeli, Alberto Maria Metelli, Francesco Trovò, Marcello Restelli. IEEE Trans. Neural Networks Learn. Syst. (2023)
Towards an AI-Based Framework for Autonomous Design and Construction: Learning from Reinforcement Learning Success in RTS Games. Ahmed Elmaraghy, Jacopo Montali, Marcello Restelli, Francesco Causone, Pierpaolo Ruttico. CAAD Futures (2023)
ARLO: A framework for Automated Reinforcement Learning. Marco Mussi, Davide Lombarda, Alberto Maria Metelli, Francesco Trovò, Marcello Restelli. Expert Syst. Appl. (2023)
Wasserstein Actor-Critic: Directed Exploration via Optimism for Continuous-Actions Control. Amarildo Likmeta, Matteo Sacco, Alberto Maria Metelli, Marcello Restelli. AAAI (2023)
Simultaneously Updating All Persistence Values in Reinforcement Learning. Luca Sabbioni, Luca Al Daire, Lorenzo Bisi, Alberto Maria Metelli, Marcello Restelli. AAAI (2023)

2022

Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization. Pierre Liotet, Francesco Vidaich, Alberto Maria Metelli, Marcello Restelli. AAAI (2022)
Safe Learning in Tree-Form Sequential Decision Making: Handling Hard and Soft Constraints. Martino Bernasconi, Federico Cacciamani, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti, Francesco Trovò. ICML (2022)
Sequential Information Design: Learning to Persuade in the Dark. Martino Bernasconi, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti, Francesco Trovò. NeurIPS (2022)
Delayed Reinforcement Learning by Imitation. Pierre Liotet, Davide Maran, Lorenzo Bisi, Marcello Restelli. ICML (2022)
Risk-averse policy optimization via risk-neutral policy optimization. Lorenzo Bisi, Davide Santambrogio, Federico Sandrelli, Andrea Tirinzoni, Brian D. Ziebart, Marcello Restelli. Artif. Intell. (2022)
A practical guide to multi-objective reinforcement learning and planning. Conor F. Hayes, Roxana Radulescu, Eugenio Bargiacchi, Johan Källström, Matthew Macfarlane, Mathieu Reymond, Timothy Verstraeten, Luisa M. Zintgraf, Richard Dazeley, Fredrik Heintz, Enda Howley, Athirai A. Irissappane, Patrick Mannion, Ann Nowé, Gabriel de Oliveira Ramos, Marcello Restelli, Peter Vamplew, Diederik M. Roijers. Auton. Agents Multi Agent Syst. (2022)
Goal-Directed Planning via Hindsight Experience Replay. Lorenzo Moro, Amarildo Likmeta, Enrico Prati, Marcello Restelli. ICLR (2022)
Learning in Markov games: Can we exploit a general-sum opponent? Giorgia Ramponi, Marcello Restelli. UAI (2022)
Off-Policy Evaluation with Deficient Support Using Side Information. Nicolò Felicioni, Maurizio Ferrari Dacrema, Marcello Restelli, Paolo Cremonesi. NeurIPS (2022)
Multi-Fidelity Best-Arm Identification. Riccardo Poiani, Alberto Maria Metelli, Marcello Restelli. NeurIPS (2022)
The Importance of Non-Markovianity in Maximum State Entropy Exploration. Mirco Mutti, Riccardo De Santi, Marcello Restelli. ICML (2022)
Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees. Andrea Tirinzoni, Matteo Papini, Ahmed Touati, Alessandro Lazaric, Matteo Pirotta. NeurIPS (2022)
Stochastic Rising Bandits. Alberto Maria Metelli, Francesco Trovò, Matteo Pirola, Marcello Restelli. ICML (2022)
Storehouse: a Reinforcement Learning Environment for Optimizing Warehouse Management. Julen Cestero, Marco Quartulli, Alberto Maria Metelli, Marcello Restelli. IJCNN (2022)
Unsupervised Reinforcement Learning in Multiple Environments. Mirco Mutti, Mattia Mancassola, Marcello Restelli. AAAI (2022)
Finite Sample Analysis of Mean-Volatility Actor-Critic for Risk-Averse Reinforcement Learning. Khaled Eldowa, Lorenzo Bisi, Marcello Restelli. AISTATS (2022)
Dark-Pool Smart Order Routing: a Combinatorial Multi-armed Bandit Approach. Martino Bernasconi, Stefano Martino, Edoardo Vittori, Francesco Trovò, Marcello Restelli. ICAIF (2022)
Pricing the Long Tail by Explainable Product Aggregation and Monotonic Bandits. Marco Mussi, Gianmarco Genalti, Francesco Trovò, Alessandro Nuara, Nicola Gatti, Marcello Restelli. KDD (2022)
A unified view of configurable Markov Decision Processes: Solution concepts, value functions, and operators. Alberto Maria Metelli. Intelligenza Artificiale (2022)
Exploiting environment configurability in reinforcement learning. Alberto Maria Metelli. N/A (2022)
Balancing Sample Efficiency and Suboptimality in Inverse Reinforcement Learning. Angelo Damiani, Giorgio Manganini, Alberto Maria Metelli, Marcello Restelli. ICML (2022)
The Evolutionary Dynamics of Soft-Max Policy Gradient in Multi-Agent Settings. Martino Bernasconi, Federico Cacciamani, Simone Fioravanti, Nicola Gatti, Francesco Trovò. AAMAS (2022)
Multi-Armed Bandit Problem with Temporally-Partitioned Rewards: When Partial Feedback Counts. Giulia Romano, Andrea Agostini, Francesco Trovò, Nicola Gatti, Marcello Restelli. IJCAI (2022)
Challenging Common Assumptions in Convex Reinforcement Learning. Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, Marcello Restelli. NeurIPS (2022)
Reward-Free Policy Space Compression for Reinforcement Learning. Mirco Mutti, Stefano Del Col, Marcello Restelli. AISTATS (2022)
Trust Region Meta Learning for Policy Optimization. Manuel Occorso, Luca Sabbioni, Alberto Maria Metelli, Marcello Restelli. Meta-Knowledge Transfer @ ECML/PKDD (2022)
Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits. Gergely Neu, Julia Olkhovskaya, Matteo Papini, Ludovic Schwartz. NeurIPS (2022)
Online joint bid/daily budget optimization of Internet advertising campaigns. Alessandro Nuara, Francesco Trovò, Nicola Gatti, Marcello Restelli. Artif. Intell. (2022)
Policy space identification in configurable environments. Alberto Maria Metelli, Guglielmo Manneschi, Marcello Restelli. Mach. Learn. (2022)
Addressing Non-Stationarity in FX Trading with Online Model Selection of Offline RL Experts. Antonio Riva, Lorenzo Bisi, Pierre Liotet, Luca Sabbioni, Edoardo Vittori, Marco Pinciroli, Michele Trapletti, Marcello Restelli. ICAIF (2022)
Smoothing policies and safe policy gradients. Matteo Papini, Matteo Pirotta, Marcello Restelli. Mach. Learn. (2022)

2021

Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and Learning. Alberto Maria Metelli, Alessio Russo, Marcello Restelli. NeurIPS (2021)
Safe policy optimization. Matteo Papini. N/A (2021)
Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate. Mirco Mutti, Lorenzo Pratissoli, Marcello Restelli. AAAI (2021)
Exploiting Opponents Under Utility Constraints in Sequential Games. Martino Bernasconi de Luca, Federico Cacciamani, Simone Fioravanti, Nicola Gatti, Alberto Marchesi, Francesco Trovò. NeurIPS (2021)
Exploiting History Data for Nonstationary Multi-armed Bandit. Gerlando Re, Fabio Chiusano, Francesco Trovò, Diego Carrera, Giacomo Boracchi, Marcello Restelli. ECML/PKDD (2021)
Conservative Online Convex Optimization. Martino Bernasconi de Luca, Edoardo Vittori, Francesco Trovò, Marcello Restelli. ECML/PKDD (2021)
Newton Optimization on Helmholtz Decomposition for Continuous Games. Giorgia Ramponi, Marcello Restelli. AAAI (2021)
Learning in Non-Cooperative Configurable Markov Decision Processes. Giorgia Ramponi, Alberto Maria Metelli, Alessandro Concetti, Marcello Restelli. NeurIPS (2021)
Learning FX trading strategies with FQI and persistent actions. Antonio Riva, Lorenzo Bisi, Pierre Liotet, Luca Sabbioni, Edoardo Vittori, Marco Pinciroli, Michele Trapletti, Marcello Restelli. ICAIF (2021)
Automated Reasoning for Reinforcement Learning Agents in Structured Environments. Alessandro Gianola, Marco Montali, Matteo Papini. OVERLAY@GandALF (2021)
Monte carlo tree search for trading and hedging. Edoardo Vittori, Amarildo Likmeta, Marcello Restelli. ICAIF (2021)
Safe Policy Iteration: A Monotonically Improving Approximate Policy Iteration Approach. Alberto Maria Metelli, Matteo Pirotta, Daniele Calandriello, Marcello Restelli. J. Mach. Learn. Res. (2021)
Provably Efficient Learning of Transferable Rewards. Alberto Maria Metelli, Giorgia Ramponi, Alessandro Concetti, Marcello Restelli. ICML (2021)
Leveraging Good Representations in Linear Contextual Bandits. Matteo Papini, Andrea Tirinzoni, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta. ICML (2021)
Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection. Matteo Papini, Andrea Tirinzoni, Aldo Pacchiano, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta. NeurIPS (2021)
MushroomRL: Simplifying Reinforcement Learning Research. Carlo D'Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters. J. Mach. Learn. Res. (2021)
Dealing with multiple experts and non-stationarity in inverse reinforcement learning: an application to real-life problems. Amarildo Likmeta, Alberto Maria Metelli, Giorgia Ramponi, Andrea Tirinzoni, Matteo Giuliani, Marcello Restelli. Mach. Learn. (2021)
Meta-Reinforcement Learning by Tracking Task Non-stationarity. Riccardo Poiani, Andrea Tirinzoni, Marcello Restelli. IJCAI (2021)
Gaussian Approximation for Bias Reduction in Q-Learning. Carlo D'Eramo, Andrea Cini, Alessandro Nuara, Matteo Pirotta, Cesare Alippi, Jan Peters, Marcello Restelli. J. Mach. Learn. Res. (2021)
Learning a Belief Representation for Delayed Reinforcement Learning. Pierre Liotet, Erick Venneri, Marcello Restelli. IJCNN (2021)
Policy Optimization as Online Learning with Mediator Feedback. Alberto Maria Metelli, Matteo Papini, Pierluca D'Oro, Marcello Restelli. AAAI (2021)
Time-variant variational transfer for value functions. Giuseppe Canonaco, Andrea Soprani, Matteo Giuliani, Andrea Castelletti, Manuel Roveri, Marcello Restelli. UAI (2021)

2020

Model-Free Non-Stationarity Detection and Adaptation in Reinforcement Learning. Giuseppe Canonaco, Marcello Restelli, Manuel Roveri. ECAI (2020)
A Novel Confidence-Based Algorithm for Structured Bandits. Andrea Tirinzoni, Alessandro Lazaric, Marcello Restelli. AISTATS (2020)
Sequential Transfer in Reinforcement Learning with a Generative Model. Andrea Tirinzoni, Riccardo Poiani, Marcello Restelli. ICML (2020)
Sharing Knowledge in Multi-Task Deep Reinforcement Learning. Carlo D'Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters. ICLR (2020)
Sliding-Window Thompson Sampling for Non-Stationary Settings. Francesco Trovò, Marcello Restelli, Nicola Gatti. J. Artif. Intell. Res. (2020)
An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits. Andrea Tirinzoni, Matteo Pirotta, Marcello Restelli, Alessandro Lazaric. NeurIPS (2020)
Foreign exchange trading: a risk-averse batch reinforcement learning approach. Lorenzo Bisi, Pierre Liotet, Luca Sabbioni, Gianmarco Reho, Nico Montali, Marcello Restelli, Cristiana Corno. ICAIF (2020)
Risk-Averse Trust Region Optimization for Reward-Volatility Reduction. Lorenzo Bisi, Luca Sabbioni, Edoardo Vittori, Matteo Papini, Marcello Restelli. IJCAI (2020)
Inferring Functional Properties from Fluid Dynamics Features. Andrea Schillaci, Maurizio Quadrio, Carlotta Pipolo, Marcello Restelli, Giacomo Boracchi. ICPR (2020)
Inverse Reinforcement Learning from a Gradient-based Learner. Giorgia Ramponi, Gianluca Drappo, Marcello Restelli. NeurIPS (2020)
Control Frequency Adaptation via Action Persistence in Batch Reinforcement Learning. Alberto Maria Metelli, Flavio Mazzolini, Lorenzo Bisi, Luca Sabbioni, Marcello Restelli. ICML (2020)
Importance Sampling Techniques for Policy Optimization. Alberto Maria Metelli, Matteo Papini, Nico Montali, Marcello Restelli. J. Mach. Learn. Res. (2020)
On the use of the policy gradient and Hessian in inverse reinforcement learning. Alberto Maria Metelli, Matteo Pirotta, Marcello Restelli. Intelligenza Artificiale (2020)
Fast direct calibration of interest rate derivatives pricing models. Luca Sabbioni, Marcello Restelli, Andrea Prampolini. ICAIF (2020)
Learning Probably Approximately Correct Maximin Strategies in Simulation-Based Games with Infinite Strategy Spaces. Alberto Marchesi, Francesco Trovò, Nicola Gatti. AAMAS (2020)
An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies. Mirco Mutti, Marcello Restelli. AAAI (2020)
Truly Batch Model-Free Inverse Reinforcement Learning about Multiple Intentions. Giorgia Ramponi, Amarildo Likmeta, Alberto Maria Metelli, Andrea Tirinzoni, Marcello Restelli. AISTATS (2020)
Gradient-Aware Model-Based Policy Search. Pierluca D'Oro, Alberto Maria Metelli, Andrea Tirinzoni, Matteo Papini, Marcello Restelli. AAAI (2020)
Balancing Learning Speed and Stability in Policy Gradient via Adaptive Exploration. Matteo Papini, Andrea Battistello, Marcello Restelli. AISTATS (2020)
Dealing with transaction costs in portfolio optimization: online gradient descent with momentum. Edoardo Vittori, Martino Bernasconi de Luca, Francesco Trovò, Marcello Restelli. ICAIF (2020)
Option hedging with risk averse reinforcement learning. Edoardo Vittori, Michele Trapletti, Marcello Restelli. ICAIF (2020)
Driving Exploration by Maximum Distribution in Gaussian Process Bandits. Alessandro Nuara, Francesco Trovò, Dominic Crippa, Nicola Gatti, Marcello Restelli. AAMAS (2020)
Combining reinforcement learning with rule-based controllers for transparent and general decision-making in autonomous driving. Amarildo Likmeta, Alberto Maria Metelli, Andrea Tirinzoni, Riccardo Giol, Marcello Restelli, Danilo Romano. Robotics Auton. Syst. (2020)

2019

Reinforcement Learning in Configurable Continuous Environments. Alberto Maria Metelli, Emanuele Ghelfi, Marcello Restelli. ICML (2019)
Optimistic Policy Optimization via Multiple Importance Sampling. Matteo Papini, Alberto Maria Metelli, Lorenzo Lupo, Marcello Restelli. ICML (2019)
Propagating Uncertainty in Reinforcement Learning via Wasserstein Barycenters. Alberto Maria Metelli, Amarildo Likmeta, Marcello Restelli. NeurIPS (2019)
Exploration Driven by an Optimistic Bellman Equation. Samuele Tosatto, Carlo D'Eramo, Joni Pajarinen, Marcello Restelli, Jan Peters. IJCNN (2019)
Transfer of Samples in Policy Search via Multiple Importance Sampling. Andrea Tirinzoni, Mattia Salvini, Marcello Restelli. ICML (2019)
Dealing with Interdependencies and Uncertainty in Multi-Channel Advertising Campaigns Optimization. Alessandro Nuara, Nicola Sosio, Francesco Trovò, Maria Chiara Zaccardi, Nicola Gatti, Marcello Restelli. WWW (2019)
Feature Selection via Mutual Information: New Theoretical Insights. Mario Beraha, Alberto Maria Metelli, Matteo Papini, Andrea Tirinzoni, Marcello Restelli. IJCNN (2019)
Exploiting Action-Value Uncertainty to Drive Exploration in Reinforcement Learning. Carlo D'Eramo, Andrea Cini, Marcello Restelli. IJCNN (2019)

2018

Transfer of Value Functions via Variational Methods. Andrea Tirinzoni, Rafael Rodríguez-Sánchez, Marcello Restelli. NeurIPS (2018)
Configurable Markov Decision Processes. Alberto Maria Metelli, Mirco Mutti, Marcello Restelli. ICML (2018)
Targeting Optimization for Internet Advertising by Learning from Logged Bandit Feedback. Margherita Gasparini, Alessandro Nuara, Francesco Trovò, Nicola Gatti, Marcello Restelli. IJCNN (2018)
Policy Optimization via Importance Sampling. Alberto Maria Metelli, Matteo Papini, Francesco Faccio, Marcello Restelli. NeurIPS (2018)
Importance Weighted Transfer of Samples in Reinforcement Learning. Andrea Tirinzoni, Andrea Sessa, Matteo Pirotta, Marcello Restelli. ICML (2018)
Does Reinforcement Learning outperform PID in the control of FES-induced elbow flex-extension? Davide Di Febbo, Emilia Ambrosini, Matteo Pirotta, Eric Rojas, Marcello Restelli, Alessandra Laura Giulia Pedrocchi, Simona Ferrante. MeMeA (2018)
A Combinatorial-Bandit Algorithm for the Online Joint Bid/Budget Optimization of Pay-per-Click Advertising Campaigns. Alessandro Nuara, Francesco Trovò, Nicola Gatti, Marcello Restelli. AAAI (2018)
Stochastic Variance-Reduced Policy Gradient. Matteo Papini, Damiano Binaghi, Giuseppe Canonaco, Matteo Pirotta, Marcello Restelli. ICML (2018)
Improving multi-armed bandit algorithms in online pricing settings. Francesco Trovò, Stefano Paladino, Marcello Restelli, Nicola Gatti. Int. J. Approx. Reason. (2018)

2017

User context estimation for public travel assistance and intelligent service scheduling. Alessio Pagani, Francesco Bruschi, Vincenzo Rana, Marcello Restelli. ITSC (2017)
Compatible Reward Inverse Reinforcement Learning. Alberto Maria Metelli, Matteo Pirotta, Marcello Restelli. NIPS (2017)
Unimodal Thompson Sampling for Graph-Structured Arms. Stefano Paladino, Francesco Trovò, Marcello Restelli, Nicola Gatti. AAAI (2017)
Estimating the Maximum Expected Value in Continuous Reinforcement Learning Problems. Carlo D'Eramo, Alessandro Nuara, Matteo Pirotta, Marcello Restelli. AAAI (2017)
Exploiting structure and uncertainty of Bellman updates in Markov decision processes. Davide Tateo, Carlo D'Eramo, Alessandro Nuara, Marcello Restelli, Andrea Bonarini. SSCI (2017)
An Ensemble Approach for Cognitive Fault Detection and Isolation in Sensor Networks. Manuel Roveri, Francesco Trovò. Int. J. Neural Syst. (2017)
Gradient-based minimization for multi-expert Inverse Reinforcement Learning. Davide Tateo, Matteo Pirotta, Marcello Restelli, Andrea Bonarini. SSCI (2017)
Adaptive Batch Size for Safe Policy Gradients. Matteo Papini, Matteo Pirotta, Marcello Restelli. NIPS (2017)
Designing Learning Algorithms over the Sequence Form of an Extensive-Form Game. Edoardo Manino, Nicola Gatti, Marcello Restelli. AAMAS (2017)
Regret Minimization Algorithms for the Followers Behaviour Identification in Leadership Games. Lorenzo Bisi, Giuseppe De Nittis, Francesco Trovò, Marcello Restelli, Nicola Gatti. UAI (2017)
Risk-averse trees for learning from logged bandit feedback. Francesco Trovò, Stefano Paladino, Paolo Simone, Marcello Restelli, Nicola Gatti. IJCNN (2017)
Boosted Fitted Q-Iteration. Samuele Tosatto, Matteo Pirotta, Carlo D'Eramo, Marcello Restelli. ICML (2017)

2016

Extensive-form games with heterogeneous populations: solution concepts, equilibria characterization, learning dynamics. Nicola Gatti, Fabio Panozzo, Marcello Restelli. Intelligenza Artificiale (2016)
Policy Search for the Optimal Control of Markov Decision Processes: A Novel Particle-Based Iterative Scheme. Giorgio Manganini, Matteo Pirotta, Marcello Restelli, Luigi Piroddi, Maria Prandini. IEEE Trans. Cybern. (2016)
Reconstruction of public transport state. Alessio Pagani, Francesco Bruschi, Vincenzo Rana, Marcello Restelli. ITSC (2016)
Budgeted Multi-Armed Bandit in Continuous Action Space. Francesco Trovò, Stefano Paladino, Marcello Restelli, Nicola Gatti. ECAI (2016)
Multi-objective Reinforcement Learning through Continuous Pareto Manifold Approximation. Simone Parisi, Matteo Pirotta, Marcello Restelli. J. Artif. Intell. Res. (2016)
Estimating Maximum Expected Value through Gaussian Approximation. Carlo D'Eramo, Marcello Restelli, Alessandro Nuara. ICML (2016)
Sequence-Form and Evolutionary Dynamics: Realization Equivalence to Agent Form and Logit Dynamics. Nicola Gatti, Marcello Restelli. AAAI (2016)
Inverse Reinforcement Learning through Policy Gradient Minimization. Matteo Pirotta, Marcello Restelli. AAAI (2016)
Making Intelligent the Embedded Systems Through Cognitive Outlier and Fault Detection. Manuel Roveri, Francesco Trovò. Advances in Neural Networks (2016)

2015

A cognitive fault detection and diagnosis system for sensor networks. Francesco Trovò. N/A (2015)
Sparse multi-task reinforcement learning. Daniele Calandriello, Alessandro Lazaric, Marcello Restelli. Intelligenza Artificiale (2015)
Truthful learning mechanisms for multi-slot sponsored search auctions with externalities. Nicola Gatti, Alessandro Lazaric, Marco Rocco, Francesco Trovò. Artif. Intell. (2015)
Policy gradient in Lipschitz Markov Decision Processes. Matteo Pirotta, Marcello Restelli, Luca Bascetta. Mach. Learn. (2015)
Following Newton direction in Policy Gradient with parameter exploration. Giorgio Manganini, Matteo Pirotta, Marcello Restelli, Luca Bascetta. IJCNN (2015)
Estimating a Mean-Path from a set of 2-D curves. Amir M. Ghalamzan E., Luca Bascetta, Marcello Restelli, Paolo Rocco. ICRA (2015)
Multi-Objective Reinforcement Learning with Continuous Pareto Frontier Approximation. Matteo Pirotta, Simone Parisi, Marcello Restelli. AAAI (2015)

2014

Evolutionary Dynamics of Q-Learning over the Sequence Form. Fabio Panozzo, Nicola Gatti, Marcello Restelli. AAAI (2014)
A Self-Building and Cluster-Based Cognitive Fault Diagnosis System for Sensor Networks. Cesare Alippi, Manuel Roveri, Francesco Trovò. IEEE Trans. Neural Networks Learn. Syst. (2014)
Sparse Multi-Task Reinforcement Learning. Daniele Calandriello, Alessandro Lazaric, Marcello Restelli. NIPS (2014)
On Power and Energy Consumption Modeling for Smart Mobile Devices. Matteo Ferroni, Andrea Cazzola, Francesco Trovò, Donatella Sciuto, Marco Domenico Santambrogio. EUC (2014)
Policy gradient approaches for multi-objective sequential decision making: A comparison. Simone Parisi, Matteo Pirotta, Nicola Smacchia, Luca Bascetta, Marcello Restelli. ADPRL (2014)
An Ensemble of HMMs for Cognitive Fault Detection in Distributed Sensor Networks. Manuel Roveri, Francesco Trovò. AIAI (2014)
Policy gradient approaches for multi-objective sequential decision making. Simone Parisi, Matteo Pirotta, Nicola Smacchia, Luca Bascetta, Marcello Restelli. IJCNN (2014)
Learning causal dependencies to etect and diagnose faults in sensor networks. Cesare Alippi, Manuel Roveri, Francesco Trovò. IES (2014)

2013

Adaptive Step-Size for Policy Gradient Methods. Matteo Pirotta, Marcello Restelli, Luca Bascetta. NIPS (2013)
Extensive-form games with heterogeneous populations. Nicola Gatti, Fabio Panozzo, Marcello Restelli. AAMAS (2013)
Safe Policy Iteration. Matteo Pirotta, Marcello Restelli, Alessio Pecorino, Daniele Calandriello. ICML (2013)
Efficient Evolutionary Dynamics with Extensive-Form Games. Nicola Gatti, Fabio Panozzo, Marcello Restelli. AAAI (2013)
Adaptive and Flexible Smartphone Power Modeling. A. A. Nacci, Francesco Trovò, Filippo Maggi, Matteo Ferroni, Andrea Cazzola, Donatella Sciuto, Marco D. Santambrogio. Mob. Networks Appl. (2013)

2012

Data-driven dynamic emulation modelling for the optimal management of environmental systems. Andrea Castelletti, Stefano Galelli, Marcello Restelli, Rodolfo Soncini-Sessa. Environ. Model. Softw. (2012)
A truthful learning mechanism for contextual multi-slot sponsored search auctions with externalities. Nicola Gatti, Alessandro Lazaric, Francesco Trovò. EC (2012)
A "Learning from Models" Cognitive Fault Diagnosis System. Cesare Alippi, Manuel Roveri, Francesco Trovò. ICANN (2012)
Computing Equilibria with Two-Player Zero-Sum Continuous Stochastic Games with Switching Controller. Guido Bonomi, Nicola Gatti, Fabio Panozzo, Marcello Restelli. AAAI (2012)
Tree-based Fitted Q-iteration for Multi-Objective Markov Decision problems. Andrea Castelletti, Francesca Pianosi, Marcello Restelli. IJCNN (2012)
A truthful learning mechanism for multi-slot sponsored search auctions with externalities. Nicola Gatti, Alessandro Lazaric, Francesco Trovò. AAMAS (2012)

2011

Transfer from Multiple MDPs. Alessandro Lazaric, Marcello Restelli. NIPS (2011)
Multi-objective fitted Q-iteration: Pareto frontier approximation in one single run. Andrea Castelletti, Francesca Pianosi, Marcello Restelli. ICNSC (2011)
Fitted policy search. Martino Migliavacca, Alessio Pecorino, Matteo Pirotta, Marcello Restelli, Andrea Bonarini. ADPRL (2011)
Tree-based variable selection for dimensionality reduction of large-scale control systems. Andrea Castelletti, Stefano Galelli, Marcello Restelli, Rodolfo Soncini-Sessa. ADPRL (2011)
Equilibrium approximation in simulation-based extensive-form games. Nicola Gatti, Marcello Restelli. AAMAS (2011)

2009

Batch Reinforcement Learning for semi-active suspension control. Simone Tognetti, Sergio M. Savaresi, Cristiano Spelta, Marcello Restelli. CCA/ISIC (2009)
Reinforcement distribution in fuzzy Q-learning. Andrea Bonarini, Alessandro Lazaric, Francesco Montrone, Marcello Restelli. Fuzzy Sets Syst. (2009)
Batch Reinforcement Learning - An Application to a Controllable Semi-active Suspension System. Simone Tognetti, Marcello Restelli, Sergio M. Savaresi, Cristiano Spelta. ICINCO-ICSO (2009)

2008

Transfer of task representation in reinforcement learning using policy-based proto-value functions. Eliseo Ferrante, Alessandro Lazaric, Marcello Restelli. AAMAS (2008)
On the usefulness of opponent modeling: the Kuhn Poker case study. Alessandro Lazaric, Mario Quaresimale, Marcello Restelli. AAMAS (2008)
Transfer of samples in batch reinforcement learning. Alessandro Lazaric, Marcello Restelli, Andrea Bonarini. ICML (2008)
Improving Batch Reinforcement Learning Performance through Transfer of Samples. Alessandro Lazaric, Marcello Restelli, Andrea Bonarini. STAIRS (2008)
Batch Reinforcement Learning for Controlling a Mobile Wheeled Pendulum Robot. Andrea Bonarini, Claudio Caccia, Alessandro Lazaric, Marcello Restelli. IFIP AI (2008)
Towards Automated Bargaining in Electronic Markets: A Partially Two-Sided Competition Model. Nicola Gatti, Alessandro Lazaric, Marcello Restelli. AMEC/TADA (2008)

2007

Reinforcement Learning in Complex Environments Through Multiple Adaptive Partitions. Andrea Bonarini, Alessandro Lazaric, Marcello Restelli. AI*IA (2007)
Reinforcement Learning in Continuous Action Spaces through Sequential Monte Carlo Methods. Alessandro Lazaric, Marcello Restelli, Andrea Bonarini. NIPS (2007)
Problems and solutions for anchoring in multi-robot applications. Andrea Bonarini, Matteo Matteucci, Marcello Restelli. J. Intell. Fuzzy Syst. (2007)
Bifurcation Analysis of Reinforcement Learning Agents in the Selten's Horse Game. Alessandro Lazaric, Enrique Munoz de Cote, Fabio Dercole, Marcello Restelli. Adaptive Agents and Multi-Agents Systems (2007)
Piecewise constant reinforcement learning for robotic applications. Andrea Bonarini, Alessandro Lazaric, Marcello Restelli. ICINCO-ICSO (2007)
Learning Fuzzy Classifier Systems: Architecture and Exploration Issues. Andrea Bonarini, Matteo Matteucci, Marcello Restelli. Int. J. Artif. Intell. Tools (2007)

2006

Concepts and fuzzy models for behavior-based robotics. Andrea Bonarini, Matteo Matteucci, Marcello Restelli. Int. J. Approx. Reason. (2006)
Incremental Skill Acquisition for Self-motivated Learning Animats. Andrea Bonarini, Alessandro Lazaric, Marcello Restelli. SAB (2006)
Learning to cooperate in multi-agent social dilemmas. Enrique Munoz de Cote, Alessandro Lazaric, Marcello Restelli. AAMAS (2006)

2005

MRT: Robotics Off-the-Shelf with the Modular Robotic Toolkit. Andrea Bonarini, Matteo Matteucci, Marcello Restelli. PPSDR@ICRA (2005)
Automatic Error Detection and Reduction for an Odometric Sensor based on Two Optical Mice. Andrea Bonarini, Matteo Matteucci, Marcello Restelli. ICRA (2005)
Reinforcement Distribution in Continuous State Action Space Fuzzy Q-Learning: A Novel Approach. Andrea Bonarini, Francesco Montrone, Marcello Restelli. WILF (2005)

2004

A kinematic-independent dead-reckoning sensor for indoor mobile robotics. Andrea Bonarini, Matteo Matteucci, Marcello Restelli. IROS (2004)
A multi-agent system for multi-agent learning. Marcello Restelli. N/A (2004)
Dead Reckoning for Mobile Robots Using Two Optical Mice. Andrea Bonarini, Matteo Matteucci, Marcello Restelli. ICINCO (2004)

2003

A Probabilistic Framework for Weighting Different Sensor Data in MUREA. Marcello Restelli, Domenico G. Sorrenti, Fabio M. Marchese. RoboCup (2003)
Filling the Gap among Coordination, Planning, and Reaction Using a Fuzzy Cognitive Model. Andrea Bonarini, Matteo Matteucci, Marcello Restelli. RoboCup (2003)
Concepts and Fuzzy Models for Behavior-Based Robotics. Andrea Bonarini, Matteo Matteucci, Marcello Restelli. WILF (2003)

2002

An architecture to implement agents co-operating in dynamic environments. Andrea Bonarini, Marcello Restelli. AAMAS (2002)
MUREA: A MUlti-Resolution Evidence Accumulation Method for Robot Localization in Known Environments. Marcello Restelli, Domenico G. Sorrenti, Fabio M. Marchese. RoboCup (2002)
A robot localization method based on evidence accumulation and multi-resolution. Marcello Restelli, Domenico G. Sorrenti, Fabio M. Marchese. IROS (2002)

2001

Concepts for Anchoring in Robotics. Andrea Bonarini, Matteo Matteucci, Marcello Restelli. AI*IA (2001)
Fun2Mas: The Milan Robocup Team. Andrea Bonarini, Giovanni Invernizzi, Fabio M. Marchese, Matteo Matteucci, Marcello Restelli, Domenico G. Sorrenti. RoboCup (2001)
A Framework for Robust Sensing in Multi-agent Systems. Andrea Bonarini, Matteo Matteucci, Marcello Restelli. RoboCup (2001)