Marcello Restelli

312 papers A* 78A 25B 15C 6Journal 140Unranked 47

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	How Log-Barrier Helps Exploration in Policy Optimization. CoRR Leonardo Cesani, Matteo Papini, Marcello Restelli
2026	J	`jnl`	K-Myriad: Jump-starting reinforcement learning with unsupervised parallel agents. CoRR Vincenzo De Paola, Mirco Mutti, Riccardo Zamboni, Marcello Restelli
2026	J	`jnl`	Learning in Markov Decision Processes with Exogenous Dynamics. CoRR Davide Maran, Davide Salaorni, Marcello Restelli
2026	J	`jnl`	Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching. CoRR Andrea Fraschini, Davide Tenedini, Riccardo Zamboni, Mirco Mutti, Marcello Restelli
2025	A	`conf`	"So, Tell Me About Your Policy...": Distillation of Interpretable Policies from Deep Reinforcement Learning Agents. ECAI Giovanni Dispoto, Paolo Bonetti, Marcello Restelli
2025	J	`jnl`	"So, Tell Me About Your Policy...": Distillation of interpretable policies from Deep Reinforcement Learning agents. CoRR Giovanni Dispoto, Paolo Bonetti, Marcello Restelli
2025	B	`conf`	A Reinforcement Learning Approach for Optimal Control in Microgrids. IJCNN Davide Salaorni, Federico Bianchi, Marcello Restelli, Francesco Trovò
2025	J	`jnl`	A Reinforcement Learning Approach for Optimal Control in Microgrids. CoRR Davide Salaorni, Federico Bianchi, Francesco Trovò, Marcello Restelli
2025	A	`conf`	Achieving $\widetilde{\mathcal{O}}(\sqrt{T})$ Regret in Average-Reward POMDPs with Known Observation Models. AISTATS Alessio Russo, Alberto Maria Metelli, Marcello Restelli
2025	J	`jnl`	Achieving ~O(√T) Regret in Average-Reward POMDPs with Known Observation Models. CoRR Alessio Russo, Alberto Maria Metelli, Marcello Restelli
2025	J	`jnl`	Building surrogate models using trajectories of agents trained by Reinforcement Learning. CoRR Julen Cestero, Marco Quartulli, Marcello Restelli
2025	A	`conf`	Efficient Exploitation of Hierarchical Structure in Sparse Reward Reinforcement Learning. AISTATS Gianluca Drappo, Arnaud Robert, Marcello Restelli, Aldo A. Faisal, Alberto Maria Metelli, Ciara Pike-Burke
2025	A*	`conf`	Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story. ICML Vincenzo De Paola, Riccardo Zamboni, Mirco Mutti, Marcello Restelli
2025	J	`jnl`	Enhancing Diversity in Parallel Agents: A Maximum State Entropy Exploration Story. CoRR Vincenzo De Paola, Riccardo Zamboni, Mirco Mutti, Marcello Restelli
2025	J	`jnl`	Factored-reward bandits with intermediate observations: Regret minimization and best arm identification. Artif. Intell. Marco Mussi, Simone Drago, Marcello Restelli, Alberto Maria Metelli
2025	J	`jnl`	From Parameters to Behavior: Unsupervised Compression of the Policy Space. CoRR Davide Tenedini, Riccardo Zamboni, Mirco Mutti, Marcello Restelli
2025	J	`jnl`	Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learning. CoRR Davide Salaorni, Vincenzo De Paola, Samuele Delpero, Giovanni Dispoto, Paolo Bonetti, Alessio Russo, Giuseppe Calcagno, Francesco Trovò, Matteo Papini, Alberto Maria Metelli, Marco Mussi, Marcello Restelli
2025	J	`jnl`	Limitations of Physics-Informed Neural Networks: a Study on Smart Grid Surrogation. CoRR Julen Cestero, Carmine Delle Femine, Kenji S. Muro, Marco Quartulli, Marcello Restelli
2025	J	`jnl`	Minimax off-policy evaluation and learning with subgaussian and differentiable importance weighting. Artif. Intell. Alberto Maria Metelli, Alessio Russo, Marcello Restelli
2025	J	`jnl`	Online Dynamic Pricing of Complementary Products. CoRR Marco Mussi, Marcello Restelli
2025	J	`jnl`	Optimizing Energy Management of Smart Grid using Reinforcement Learning aided by Surrogate models built using Physics-informed Neural Networks. CoRR Julen Cestero, Carmine Delle Femine, Kenji S. Muro, Marco Quartulli, Marcello Restelli
2025	J	`jnl`	Power Grid Control with Graph-Based Distributed Reinforcement Learning. CoRR Carlo Fabrizio, Gianvito Losapio, Marco Mussi, Alberto Maria Metelli, Marcello Restelli
2025	J	`jnl`	Scalable Multi-Agent Offline Reinforcement Learning and the Role of Information. CoRR Riccardo Zamboni, Enrico Brunetti, Marcello Restelli
2025	J	`jnl`	Search or split: policy gradient with adaptive policy space. Mach. Learn. Gianmarco Tedeschi, Matteo Papini, Alberto Maria Metelli, Marcello Restelli
2025	J	`jnl`	Towards Principled Multi-Agent Task Agnostic Exploration. CoRR Riccardo Zamboni, Mirco Mutti, Marcello Restelli
2024	J	`jnl`	A Provably Efficient Option-Based Algorithm for both High-Level and Low-Level Learning. RLJ Gianluca Drappo, Alberto Maria Metelli, Marcello Restelli
2024	J	`jnl`	A Provably Efficient Option-Based Algorithm for both High-Level and Low-Level Learning. CoRR Gianluca Drappo, Alberto Maria Metelli, Marcello Restelli
2024	A*	`conf`	A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics. NeurIPS 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
2024	J	`jnl`	A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics. CoRR Puze Liu, Jonas Guenster, 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 Peters
2024	J	`jnl`	A parametric algorithm is optimal for non-parametric regression of smooth functions. CoRR Davide Maran, Marcello Restelli
2024	A	`conf`	Autoregressive Bandits. AISTATS Francesco Bacchiocchi, Gianmarco Genalti, Davide Maran, Marco Mussi, Marcello Restelli, Nicola Gatti, Alberto Maria Metelli
2024	A*	`conf`	Bandits with Ranking Feedback. NeurIPS Davide Maran, Francesco Bacchiocchi, Francesco Emanuele Stradi, Matteo Castiglioni, Nicola Gatti, Marcello Restelli
2024	A*	`conf`	Best Arm Identification for Stochastic Rising Bandits. ICML Marco Mussi, Alessandro Montenegro, Francesco Trovò, Marcello Restelli, Alberto Maria Metelli
2024	J	`jnl`	Bridging Rested and Restless Bandits with Graph-Triggering: Rising and Rotting. CoRR Gianmarco Genalti, Marco Mussi, Nicola Gatti, Marcello Restelli, Matteo Castiglioni, Alberto Maria Metelli
2024	—	`conf`	Building Surrogate Models Using Trajectories of Agents Trained by Reinforcement Learning. ICANN (4) Julen Cestero, Marco Quartulli, Marcello Restelli
2024	B	`conf`	Causal Feature Selection via Transfer Entropy. IJCNN Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli
2024	J	`jnl`	Efficient Learning of POMDPs with Known Observation Model in Average-Reward Setting. CoRR Alessio Russo, Alberto Maria Metelli, Marcello Restelli
2024	A*	`conf`	Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning. ICLR Mirco Mutti, Riccardo De Santi, Marcello Restelli, Alexander Marx, Giorgia Ramponi
2024	J	`jnl`	Exploiting Risk-Aversion and Size-dependent fees in FX Trading with Fitted Natural Actor-Critic. CoRR Vito Alessandro Monaco, Antonio Riva, Luca Sabbioni, Lorenzo Bisi, Edoardo Vittori, Marco Pinciroli, Michele Trapletti, Marcello Restelli
2024	A*	`conf`	Factored-Reward Bandits with Intermediate Observations. ICML Marco Mussi, Simone Drago, Marcello Restelli, Alberto Maria Metelli
2024	A*	`conf`	Graph-Triggered Rising Bandits. ICML Gianmarco Genalti, Marco Mussi, Nicola Gatti, Marcello Restelli, Matteo Castiglioni, Alberto Maria Metelli
2024	A*	`conf`	How to Explore with Belief: State Entropy Maximization in POMDPs. ICML Riccardo Zamboni, Duilio Cirino, Marcello Restelli, Mirco Mutti
2024	J	`jnl`	How to Explore with Belief: State Entropy Maximization in POMDPs. CoRR Riccardo Zamboni, Duilio Cirino, Marcello Restelli, Mirco Mutti
2024	J	`jnl`	Information Capacity Regret Bounds for Bandits with Mediator Feedback. CoRR Khaled Eldowa, Nicolò Cesa-Bianchi, Alberto Maria Metelli, Marcello Restelli
2024	J	`jnl`	Information Capacity Regret Bounds for Bandits with Mediator Feedback. J. Mach. Learn. Res. Khaled Eldowa, Nicolò Cesa-Bianchi, Alberto Maria Metelli, Marcello Restelli
2024	J	`jnl`	Interpetable Target-Feature Aggregation for Multi-Task Learning based on Bias-Variance Analysis. CoRR Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli
2024	—	`conf`	Interpetable Target-Feature Aggregation for Multi-task Learning Based on Bias-Variance Analysis. ECML/PKDD (6) Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli
2024	J	`jnl`	Interpretable linear dimensionality reduction based on bias-variance analysis. Data Min. Knowl. Discov. Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli
2024	J	`jnl`	Inverse Reinforcement Learning with Sub-optimal Experts. CoRR Riccardo Poiani, Gabriele Curti, Alberto Maria Metelli, Marcello Restelli
2024	A*	`conf`	Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs. NeurIPS Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restelli
2024	J	`jnl`	Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs. CoRR Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restelli
2024	A*	`conf`	No-Regret Reinforcement Learning in Smooth MDPs. ICML Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restelli
2024	J	`jnl`	No-Regret Reinforcement Learning in Smooth MDPs. CoRR Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restelli
2024	A*	`conf`	Online Markov Decision Processes Configuration with Continuous Decision Space. AAAI Davide Maran, Pierriccardo Olivieri, Francesco Emanuele Stradi, Giuseppe Urso, Nicola Gatti, Marcello Restelli
2024	A*	`conf`	Optimal Multi-Fidelity Best-Arm Identification. NeurIPS Riccardo Poiani, Rémy Degenne, Emilie Kaufmann, Alberto Maria Metelli, Marcello Restelli
2024	J	`jnl`	Optimal Multi-Fidelity Best-Arm Identification. CoRR Riccardo Poiani, Rémy Degenne, Emilie Kaufmann, Alberto Maria Metelli, Marcello Restelli
2024	J	`jnl`	Optimizing Empty Container Repositioning and Fleet Deployment via Configurable Semi-POMDPs. IEEE Trans. Intell. Transp. Syst. Riccardo Poiani, Ciprian Stirbu, Alberto Maria Metelli, Marcello Restelli
2024	A*	`conf`	Parameterized Projected Bellman Operator. AAAI Théo Vincent, Alberto Maria Metelli, Boris Belousov, Jan Peters, Marcello Restelli, Carlo D'Eramo
2024	J	`jnl`	Policy Gradient with Active Importance Sampling. RLJ Matteo Papini, Giorgio Manganini, Alberto Maria Metelli, Marcello Restelli
2024	J	`jnl`	Policy Gradient with Active Importance Sampling. CoRR Matteo Papini, Giorgio Manganini, Alberto Maria Metelli, Marcello Restelli
2024	A*	`conf`	Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs. COLT Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restelli
2024	J	`jnl`	Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs. CoRR Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restelli
2024	J	`jnl`	Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds. Mach. Learn. Gabor Paczolay, Matteo Papini, Alberto Maria Metelli, István Á. Harmati, Marcello Restelli
2024	J	`jnl`	Sharing Knowledge in Multi-Task Deep Reinforcement Learning. CoRR Carlo D'Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters
2024	J	`jnl`	State and Action Factorization in Power Grids. CoRR Gianvito Losapio, Davide Beretta, Marco Mussi, Alberto Maria Metelli, Marcello Restelli
2024	J	`jnl`	Statistical Analysis of Policy Space Compression Problem. CoRR Majid Molaei, Marcello Restelli, Alberto Maria Metelli, Matteo Papini
2024	A*	`conf`	Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning. NeurIPS Riccardo Poiani, Gabriele Curti, Alberto Maria Metelli, Marcello Restelli
2024	J	`jnl`	Switching Latent Bandits. Trans. Mach. Learn. Res. Alessio Russo, Alberto Maria Metelli, Marcello Restelli
2024	J	`jnl`	The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough. RLJ Riccardo Zamboni, Duilio Cirino, Marcello Restelli, Mirco Mutti
2024	J	`jnl`	The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough. CoRR Riccardo Zamboni, Duilio Cirino, Marcello Restelli, Mirco Mutti
2024	B	`conf`	The Power of Hybrid Learning in Industrial Robotics: Efficient Grasping Strategies with Supervised-Driven Reinforcement Learning. IJCNN Vincenzo De Paola, Giuseppe Calcagno, Alberto Maria Metelli, Marcello Restelli
2024	C	`conf`	Transfer Learning for Dynamical Systems Models via Autoencoders and GANs. ACC Angelo Damiani, Gustavo Viera-López, Giorgio Manganini, Alberto Maria Metelli, Marcello Restelli
2024	J	`jnl`	Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach. CoRR Riccardo Poiani, Nicole Nobili, Alberto Maria Metelli, Marcello Restelli
2023	A	`conf`	A Brief Guide to Multi-Objective Reinforcement Learning and Planning. AAMAS 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
2023	A	`conf`	A Tale of Sampling and Estimation in Discounted Reinforcement Learning. AISTATS Alberto Maria Metelli, Mirco Mutti, Marcello Restelli
2023	J	`jnl`	A Tale of Sampling and Estimation in Discounted Reinforcement Learning. CoRR Alberto Maria Metelli, Mirco Mutti, Marcello Restelli
2023	J	`jnl`	ARLO: A framework for Automated Reinforcement Learning. Expert Syst. Appl. Marco Mussi, Davide Lombarda, Alberto Maria Metelli, Francesco Trovò, Marcello Restelli
2023	J	`jnl`	An Option-Dependent Analysis of Regret Minimization Algorithms in Finite-Horizon Semi-MDP. Trans. Mach. Learn. Res. Gianluca Drappo, Alberto Maria Metelli, Marcello Restelli
2023	J	`jnl`	An Option-Dependent Analysis of Regret Minimization Algorithms in Finite-Horizon Semi-Markov Decision Processes. CoRR Gianluca Drappo, Alberto Maria Metelli, Marcello Restelli
2023	J	`jnl`	Best Arm Identification for Stochastic Rising Bandits. CoRR Marco Mussi, Alessandro Montenegro, Francesco Trovò, Marcello Restelli, Alberto Maria Metelli
2023	J	`jnl`	Causal Feature Selection via Transfer Entropy. CoRR Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli
2023	J	`jnl`	Convex Reinforcement Learning in Finite Trials. J. Mach. Learn. Res. Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, Marcello Restelli
2023	A*	`conf`	Distributional Policy Evaluation: a Maximum Entropy approach to Representation Learning. NeurIPS Riccardo Zamboni, Alberto Maria Metelli, Marcello Restelli
2023	A*	`conf`	Dynamic Pricing with Volume Discounts in Online Settings. AAAI Marco Mussi, Gianmarco Genalti, Alessandro Nuara, Francesco Trovò, Marcello Restelli, Nicola Gatti
2023	A*	`conf`	Dynamical Linear Bandits. ICML Marco Mussi, Alberto Maria Metelli, Marcello Restelli
2023	J	`jnl`	Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning. CoRR Mirco Mutti, Riccardo De Santi, Marcello Restelli, Alexander Marx, Giorgia Ramponi
2023	J	`jnl`	IWDA: Importance Weighting for Drift Adaptation in Streaming Supervised Learning Problems. IEEE Trans. Neural Networks Learn. Syst. Filippo Fedeli, Alberto Maria Metelli, Francesco Trovò, Marcello Restelli
2023	B	`conf`	Information-Theoretic Regret Bounds for Bandits with Fixed Expert Advice. ITW Khaled Eldowa, Nicolò Cesa-Bianchi, Alberto Maria Metelli, Marcello Restelli
2023	J	`jnl`	Information-Theoretic Regret Bounds for Bandits with Fixed Expert Advice. CoRR Khaled Eldowa, Nicolò Cesa-Bianchi, Alberto Maria Metelli, Marcello Restelli
2023	J	`jnl`	Interpretable Linear Dimensionality Reduction based on Bias-Variance Analysis. CoRR Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli
2023	J	`jnl`	Nonlinear Feature Aggregation: Two Algorithms driven by Theory. CoRR Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli
2023	A	`conf`	On the Relation between Policy Improvement and Off-Policy Minimum-Variance Policy Evaluation. UAI Alberto Maria Metelli, Samuele Meta, Marcello Restelli
2023	J	`jnl`	Parameterized Projected Bellman Operator. CoRR Théo Vincent, Alberto Maria Metelli, Boris Belousov, Jan Peters, Marcello Restelli, Carlo D'Eramo
2023	A*	`conf`	Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization. AAAI Mirco Mutti, Riccardo De Santi, Emanuele Rossi, Juan Felipe Calderón, Michael M. Bronstein, Marcello Restelli
2023	J	`jnl`	Pure Exploration under Mediators' Feedback. CoRR Riccardo Poiani, Alberto Maria Metelli, Marcello Restelli
2023	J	`jnl`	Risk-averse optimization of reward-based coherent risk measures. Artif. Intell. Massimiliano Bonetti, Lorenzo Bisi, Marcello Restelli
2023	A*	`conf`	Simultaneously Updating All Persistence Values in Reinforcement Learning. AAAI Luca Sabbioni, Luca Al Daire, Lorenzo Bisi, Alberto Maria Metelli, Marcello Restelli
2023	—	`conf`	Stepsize Learning for Policy Gradient Methods in Contextual Markov Decision Processes. ECML/PKDD (4) Luca Sabbioni, Francesco Corda, Marcello Restelli
2023	J	`jnl`	Stepsize Learning for Policy Gradient Methods in Contextual Markov Decision Processes. CoRR Luca Sabbioni, Francesco Corda, Marcello Restelli
2023	A*	`conf`	Tight Performance Guarantees of Imitator Policies with Continuous Actions. AAAI Davide Maran, Alberto Maria Metelli, Marcello Restelli
2023	A*	`conf`	Towards Theoretical Understanding of Inverse Reinforcement Learning. ICML Alberto Maria Metelli, Filippo Lazzati, Marcello Restelli
2023	J	`jnl`	Towards Theoretical Understanding of Inverse Reinforcement Learning. CoRR Alberto Maria Metelli, Filippo Lazzati, Marcello Restelli
2023	—	`conf`	Towards an AI-Based Framework for Autonomous Design and Construction: Learning from Reinforcement Learning Success in RTS Games. CAAD Futures Ahmed Elmaraghy, Jacopo Montali, Marcello Restelli, Francesco Causone, Pierpaolo Ruttico
2023	A*	`conf`	Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach. NeurIPS Riccardo Poiani, Nicole Nobili, Alberto Maria Metelli, Marcello Restelli
2023	A*	`conf`	Truncating Trajectories in Monte Carlo Reinforcement Learning. ICML Riccardo Poiani, Alberto Maria Metelli, Marcello Restelli
2023	J	`jnl`	Truncating Trajectories in Monte Carlo Reinforcement Learning. CoRR Riccardo Poiani, Alberto Maria Metelli, Marcello Restelli
2023	A*	`conf`	Wasserstein Actor-Critic: Directed Exploration via Optimism for Continuous-Actions Control. AAAI Amarildo Likmeta, Matteo Sacco, Alberto Maria Metelli, Marcello Restelli
2023	J	`jnl`	Wasserstein Actor-Critic: Directed Exploration via Optimism for Continuous-Actions Control. CoRR Amarildo Likmeta, Matteo Sacco, Alberto Maria Metelli, Marcello Restelli
2022	J	`jnl`	A practical guide to multi-objective reinforcement learning and planning. Auton. Agents Multi Agent Syst. 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
2022	J	`jnl`	ARLO: A Framework for Automated Reinforcement Learning. CoRR Marco Mussi, Davide Lombarda, Alberto Maria Metelli, Francesco Trovò, Marcello Restelli
2022	—	`conf`	Addressing Non-Stationarity in FX Trading with Online Model Selection of Offline RL Experts. ICAIF Antonio Riva, Lorenzo Bisi, Pierre Liotet, Luca Sabbioni, Edoardo Vittori, Marco Pinciroli, Michele Trapletti, Marcello Restelli
2022	J	`jnl`	Analysis, Characterization, Prediction and Attribution of Extreme Atmospheric Events with Machine Learning: a Review. CoRR Sancho Salcedo-Sanz, Jorge Pérez-Aracil, Guido Ascenso, Javier Del Ser, David Casillas-Pérez, Christopher Kadow, Dusan Fister, David Barriopedro, Ricardo García-Herrera, Marcello Restelli, Matteo Giuliani, Andrea Castelletti
2022	J	`jnl`	Autoregressive Bandits. CoRR Francesco Bacchiocchi, Gianmarco Genalti, Davide Maran, Marco Mussi, Marcello Restelli, Nicola Gatti, Alberto Maria Metelli
2022	A*	`conf`	Balancing Sample Efficiency and Suboptimality in Inverse Reinforcement Learning. ICML Angelo Damiani, Giorgio Manganini, Alberto Maria Metelli, Marcello Restelli
2022	A*	`conf`	Challenging Common Assumptions in Convex Reinforcement Learning. NeurIPS Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, Marcello Restelli
2022	J	`jnl`	Challenging Common Assumptions in Convex Reinforcement Learning. CoRR Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, Marcello Restelli
2022	—	`conf`	Dark-Pool Smart Order Routing: a Combinatorial Multi-armed Bandit Approach. ICAIF Martino Bernasconi, Stefano Martino, Edoardo Vittori, Francesco Trovò, Marcello Restelli
2022	A*	`conf`	Delayed Reinforcement Learning by Imitation. ICML Pierre Liotet, Davide Maran, Lorenzo Bisi, Marcello Restelli
2022	J	`jnl`	Delayed Reinforcement Learning by Imitation. CoRR Pierre Liotet, Davide Maran, Lorenzo Bisi, Marcello Restelli
2022	J	`jnl`	Dynamic Pricing with Volume Discounts in Online Settings. CoRR Marco Mussi, Gianmarco Genalti, Alessandro Nuara, Francesco Trovò, Marcello Restelli, Nicola Gatti
2022	J	`jnl`	Dynamical Linear Bandits. CoRR Marco Mussi, Alberto Maria Metelli, Marcello Restelli
2022	A	`conf`	Finite Sample Analysis of Mean-Volatility Actor-Critic for Risk-Averse Reinforcement Learning. AISTATS Khaled Eldowa, Lorenzo Bisi, Marcello Restelli
2022	A*	`conf`	Goal-Directed Planning via Hindsight Experience Replay. ICLR Lorenzo Moro, Amarildo Likmeta, Enrico Prati, Marcello Restelli
2022	A	`conf`	Learning in Markov games: Can we exploit a general-sum opponent? UAI Giorgia Ramponi, Marcello Restelli
2022	A*	`conf`	Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization. AAAI Pierre Liotet, Francesco Vidaich, Alberto Maria Metelli, Marcello Restelli
2022	A*	`conf`	Multi-Armed Bandit Problem with Temporally-Partitioned Rewards: When Partial Feedback Counts. IJCAI Giulia Romano, Andrea Agostini, Francesco Trovò, Nicola Gatti, Marcello Restelli
2022	J	`jnl`	Multi-Armed Bandit Problem with Temporally-Partitioned Rewards: When Partial Feedback Counts. CoRR Giulia Romano, Andrea Agostini, Francesco Trovò, Nicola Gatti, Marcello Restelli
2022	A*	`conf`	Multi-Fidelity Best-Arm Identification. NeurIPS Riccardo Poiani, Alberto Maria Metelli, Marcello Restelli
2022	A*	`conf`	Off-Policy Evaluation with Deficient Support Using Side Information. NeurIPS Nicolò Felicioni, Maurizio Ferrari Dacrema, Marcello Restelli, Paolo Cremonesi
2022	J	`jnl`	Online joint bid/daily budget optimization of Internet advertising campaigns. Artif. Intell. Alessandro Nuara, Francesco Trovò, Nicola Gatti, Marcello Restelli
2022	J	`jnl`	Optimizing Empty Container Repositioning and Fleet Deployment via Configurable Semi-POMDPs. CoRR Riccardo Poiani, Ciprian Stirbu, Alberto Maria Metelli, Marcello Restelli
2022	J	`jnl`	Policy space identification in configurable environments. Mach. Learn. Alberto Maria Metelli, Guglielmo Manneschi, Marcello Restelli
2022	A*	`conf`	Pricing the Long Tail by Explainable Product Aggregation and Monotonic Bandits. KDD Marco Mussi, Gianmarco Genalti, Francesco Trovò, Alessandro Nuara, Nicola Gatti, Marcello Restelli
2022	J	`jnl`	Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization. CoRR Mirco Mutti, Riccardo De Santi, Emanuele Rossi, Juan Felipe Calderón, Michael M. Bronstein, Marcello Restelli
2022	A	`conf`	Reward-Free Policy Space Compression for Reinforcement Learning. AISTATS Mirco Mutti, Stefano Del Col, Marcello Restelli
2022	J	`jnl`	Reward-Free Policy Space Compression for Reinforcement Learning. CoRR Mirco Mutti, Stefano Del Col, Marcello Restelli
2022	J	`jnl`	Risk-averse policy optimization via risk-neutral policy optimization. Artif. Intell. Lorenzo Bisi, Davide Santambrogio, Federico Sandrelli, Andrea Tirinzoni, Brian D. Ziebart, Marcello Restelli
2022	J	`jnl`	Simultaneously Updating All Persistence Values in Reinforcement Learning. CoRR Luca Sabbioni, Luca Al Daire, Lorenzo Bisi, Alberto Maria Metelli, Marcello Restelli
2022	J	`jnl`	Smoothing policies and safe policy gradients. Mach. Learn. Matteo Papini, Matteo Pirotta, Marcello Restelli
2022	A*	`conf`	Stochastic Rising Bandits. ICML Alberto Maria Metelli, Francesco Trovò, Matteo Pirola, Marcello Restelli
2022	J	`jnl`	Stochastic Rising Bandits. CoRR Alberto Maria Metelli, Francesco Trovò, Matteo Pirola, Marcello Restelli
2022	B	`conf`	Storehouse: a Reinforcement Learning Environment for Optimizing Warehouse Management. IJCNN Julen Cestero, Marco Quartulli, Alberto Maria Metelli, Marcello Restelli
2022	J	`jnl`	Storehouse: a Reinforcement Learning Environment for Optimizing Warehouse Management. CoRR Julen Cestero, Marco Quartulli, Alberto Maria Metelli, Marcello Restelli
2022	A*	`conf`	The Importance of Non-Markovianity in Maximum State Entropy Exploration. ICML Mirco Mutti, Riccardo De Santi, Marcello Restelli
2022	J	`jnl`	The Importance of Non-Markovianity in Maximum State Entropy Exploration. CoRR Mirco Mutti, Riccardo De Santi, Marcello Restelli
2022	J	`jnl`	Tight Performance Guarantees of Imitator Policies with Continuous Actions. CoRR Davide Maran, Alberto Maria Metelli, Marcello Restelli
2022	—	`conf`	Trust Region Meta Learning for Policy Optimization. Meta-Knowledge Transfer @ ECML/PKDD Manuel Occorso, Luca Sabbioni, Alberto Maria Metelli, Marcello Restelli
2022	A*	`conf`	Unsupervised Reinforcement Learning in Multiple Environments. AAAI Mirco Mutti, Mattia Mancassola, Marcello Restelli
2021	J	`jnl`	A Practical Guide to Multi-Objective Reinforcement Learning and Planning. CoRR 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
2021	—	`conf`	Conservative Online Convex Optimization. ECML/PKDD (1) Martino Bernasconi de Luca, Edoardo Vittori, Francesco Trovò, Marcello Restelli
2021	J	`jnl`	Dealing with multiple experts and non-stationarity in inverse reinforcement learning: an application to real-life problems. Mach. Learn. Amarildo Likmeta, Alberto Maria Metelli, Giorgia Ramponi, Andrea Tirinzoni, Matteo Giuliani, Marcello Restelli
2021	—	`conf`	Exploiting History Data for Nonstationary Multi-armed Bandit. ECML/PKDD (1) Gerlando Re, Fabio Chiusano, Francesco Trovò, Diego Carrera, Giacomo Boracchi, Marcello Restelli
2021	J	`jnl`	Gaussian Approximation for Bias Reduction in Q-Learning. J. Mach. Learn. Res. Carlo D'Eramo, Andrea Cini, Alessandro Nuara, Matteo Pirotta, Cesare Alippi, Jan Peters, Marcello Restelli
2021	—	`conf`	Learning FX trading strategies with FQI and persistent actions. ICAIF Antonio Riva, Lorenzo Bisi, Pierre Liotet, Luca Sabbioni, Edoardo Vittori, Marco Pinciroli, Michele Trapletti, Marcello Restelli
2021	B	`conf`	Learning a Belief Representation for Delayed Reinforcement Learning. IJCNN Pierre Liotet, Erick Venneri, Marcello Restelli
2021	A*	`conf`	Learning in Non-Cooperative Configurable Markov Decision Processes. NeurIPS Giorgia Ramponi, Alberto Maria Metelli, Alessandro Concetti, Marcello Restelli
2021	A*	`conf`	Leveraging Good Representations in Linear Contextual Bandits. ICML Matteo Papini, Andrea Tirinzoni, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta
2021	J	`jnl`	Leveraging Good Representations in Linear Contextual Bandits. CoRR Matteo Papini, Andrea Tirinzoni, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta
2021	J	`jnl`	Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization. CoRR Pierre Liotet, Francesco Vidaich, Alberto Maria Metelli, Marcello Restelli
2021	A*	`conf`	Meta-Reinforcement Learning by Tracking Task Non-stationarity. IJCAI Riccardo Poiani, Andrea Tirinzoni, Marcello Restelli
2021	J	`jnl`	Meta-Reinforcement Learning by Tracking Task Non-stationarity. CoRR Riccardo Poiani, Andrea Tirinzoni, Marcello Restelli
2021	—	`conf`	Monte carlo tree search for trading and hedging. ICAIF Edoardo Vittori, Amarildo Likmeta, Marcello Restelli
2021	J	`jnl`	MushroomRL: Simplifying Reinforcement Learning Research. J. Mach. Learn. Res. Carlo D'Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters
2021	A*	`conf`	Newton Optimization on Helmholtz Decomposition for Continuous Games. AAAI Giorgia Ramponi, Marcello Restelli
2021	A*	`conf`	Policy Optimization as Online Learning with Mediator Feedback. AAAI Alberto Maria Metelli, Matteo Papini, Pierluca D'Oro, Marcello Restelli
2021	A*	`conf`	Provably Efficient Learning of Transferable Rewards. ICML Alberto Maria Metelli, Giorgia Ramponi, Alessandro Concetti, Marcello Restelli
2021	A*	`conf`	Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection. NeurIPS Matteo Papini, Andrea Tirinzoni, Aldo Pacchiano, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta
2021	J	`jnl`	Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection. CoRR Matteo Papini, Andrea Tirinzoni, Aldo Pacchiano, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta
2021	J	`jnl`	Safe Policy Iteration: A Monotonically Improving Approximate Policy Iteration Approach. J. Mach. Learn. Res. Alberto Maria Metelli, Matteo Pirotta, Daniele Calandriello, Marcello Restelli
2021	A*	`conf`	Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and Learning. NeurIPS Alberto Maria Metelli, Alessio Russo, Marcello Restelli
2021	A*	`conf`	Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate. AAAI Mirco Mutti, Lorenzo Pratissoli, Marcello Restelli
2021	A	`conf`	Time-variant variational transfer for value functions. UAI Giuseppe Canonaco, Andrea Soprani, Matteo Giuliani, Andrea Castelletti, Manuel Roveri, Marcello Restelli
2021	J	`jnl`	Unsupervised Reinforcement Learning in Multiple Environments. CoRR Mirco Mutti, Mattia Mancassola, Marcello Restelli
2020	A	`conf`	A Novel Confidence-Based Algorithm for Structured Bandits. AISTATS Andrea Tirinzoni, Alessandro Lazaric, Marcello Restelli
2020	J	`jnl`	A Novel Confidence-Based Algorithm for Structured Bandits. CoRR Andrea Tirinzoni, Alessandro Lazaric, Marcello Restelli
2020	J	`jnl`	A Policy Gradient Method for Task-Agnostic Exploration. CoRR Mirco Mutti, Lorenzo Pratissoli, Marcello Restelli
2020	A*	`conf`	An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits. NeurIPS Andrea Tirinzoni, Matteo Pirotta, Marcello Restelli, Alessandro Lazaric
2020	J	`jnl`	An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits. CoRR Andrea Tirinzoni, Matteo Pirotta, Marcello Restelli, Alessandro Lazaric
2020	A*	`conf`	An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies. AAAI Mirco Mutti, Marcello Restelli
2020	A	`conf`	Balancing Learning Speed and Stability in Policy Gradient via Adaptive Exploration. AISTATS Matteo Papini, Andrea Battistello, Marcello Restelli
2020	J	`jnl`	Combining reinforcement learning with rule-based controllers for transparent and general decision-making in autonomous driving. Robotics Auton. Syst. Amarildo Likmeta, Alberto Maria Metelli, Andrea Tirinzoni, Riccardo Giol, Marcello Restelli, Danilo Romano
2020	A*	`conf`	Control Frequency Adaptation via Action Persistence in Batch Reinforcement Learning. ICML Alberto Maria Metelli, Flavio Mazzolini, Lorenzo Bisi, Luca Sabbioni, Marcello Restelli
2020	J	`jnl`	Control Frequency Adaptation via Action Persistence in Batch Reinforcement Learning. CoRR Alberto Maria Metelli, Flavio Mazzolini, Lorenzo Bisi, Luca Sabbioni, Marcello Restelli
2020	—	`conf`	Dealing with transaction costs in portfolio optimization: online gradient descent with momentum. ICAIF Edoardo Vittori, Martino Bernasconi de Luca, Francesco Trovò, Marcello Restelli
2020	A	`conf`	Driving Exploration by Maximum Distribution in Gaussian Process Bandits. AAMAS Alessandro Nuara, Francesco Trovò, Dominic Crippa, Nicola Gatti, Marcello Restelli
2020	—	`conf`	Fast direct calibration of interest rate derivatives pricing models. ICAIF Luca Sabbioni, Marcello Restelli, Andrea Prampolini
2020	—	`conf`	Foreign exchange trading: a risk-averse batch reinforcement learning approach. ICAIF Lorenzo Bisi, Pierre Liotet, Luca Sabbioni, Gianmarco Reho, Nico Montali, Marcello Restelli, Cristiana Corno
2020	A*	`conf`	Gradient-Aware Model-Based Policy Search. AAAI Pierluca D'Oro, Alberto Maria Metelli, Andrea Tirinzoni, Matteo Papini, Marcello Restelli
2020	J	`jnl`	Importance Sampling Techniques for Policy Optimization. J. Mach. Learn. Res. Alberto Maria Metelli, Matteo Papini, Nico Montali, Marcello Restelli
2020	B	`conf`	Inferring Functional Properties from Fluid Dynamics Features. ICPR Andrea Schillaci, Maurizio Quadrio, Carlotta Pipolo, Marcello Restelli, Giacomo Boracchi
2020	A*	`conf`	Inverse Reinforcement Learning from a Gradient-based Learner. NeurIPS Giorgia Ramponi, Gianluca Drappo, Marcello Restelli
2020	J	`jnl`	Inverse Reinforcement Learning from a Gradient-based Learner. CoRR Giorgia Ramponi, Gianluca Drappo, Marcello Restelli
2020	A	`conf`	Model-Free Non-Stationarity Detection and Adaptation in Reinforcement Learning. ECAI Giuseppe Canonaco, Marcello Restelli, Manuel Roveri
2020	J	`jnl`	MushroomRL: Simplifying Reinforcement Learning Research. CoRR Carlo D'Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters
2020	J	`jnl`	Newton-based Policy Optimization for Games. CoRR Giorgia Ramponi, Marcello Restelli
2020	J	`jnl`	On the use of the policy gradient and Hessian in inverse reinforcement learning. Intelligenza Artificiale Alberto Maria Metelli, Matteo Pirotta, Marcello Restelli
2020	J	`jnl`	Online Joint Bid/Daily Budget Optimization of Internet Advertising Campaigns. CoRR Alessandro Nuara, Francesco Trovò, Nicola Gatti, Marcello Restelli
2020	J	`jnl`	Option Hedging with Risk Averse Reinforcement Learning. CoRR Edoardo Vittori, Michele Trapletti, Marcello Restelli
2020	—	`conf`	Option hedging with risk averse reinforcement learning. ICAIF Edoardo Vittori, Michele Trapletti, Marcello Restelli
2020	J	`jnl`	Policy Optimization as Online Learning with Mediator Feedback. CoRR Alberto Maria Metelli, Matteo Papini, Pierluca D'Oro, Marcello Restelli
2020	A*	`conf`	Risk-Averse Trust Region Optimization for Reward-Volatility Reduction. IJCAI Lorenzo Bisi, Luca Sabbioni, Edoardo Vittori, Matteo Papini, Marcello Restelli
2020	A*	`conf`	Sequential Transfer in Reinforcement Learning with a Generative Model. ICML Andrea Tirinzoni, Riccardo Poiani, Marcello Restelli
2020	J	`jnl`	Sequential Transfer in Reinforcement Learning with a Generative Model. CoRR Andrea Tirinzoni, Riccardo Poiani, Marcello Restelli
2020	A*	`conf`	Sharing Knowledge in Multi-Task Deep Reinforcement Learning. ICLR Carlo D'Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters
2020	J	`jnl`	Sliding-Window Thompson Sampling for Non-Stationary Settings. J. Artif. Intell. Res. Francesco Trovò, Marcello Restelli, Nicola Gatti
2020	J	`jnl`	Time-Variant Variational Transfer for Value Functions. CoRR Giuseppe Canonaco, Andrea Soprani, Manuel Roveri, Marcello Restelli
2020	A	`conf`	Truly Batch Model-Free Inverse Reinforcement Learning about Multiple Intentions. AISTATS Giorgia Ramponi, Amarildo Likmeta, Alberto Maria Metelli, Andrea Tirinzoni, Marcello Restelli
2019	J	`jnl`	An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies. CoRR Mirco Mutti, Marcello Restelli
2019	A*	`conf`	Dealing with Interdependencies and Uncertainty in Multi-Channel Advertising Campaigns Optimization. WWW Alessandro Nuara, Nicola Sosio, Francesco Trovò, Maria Chiara Zaccardi, Nicola Gatti, Marcello Restelli
2019	B	`conf`	Exploiting Action-Value Uncertainty to Drive Exploration in Reinforcement Learning. IJCNN Carlo D'Eramo, Andrea Cini, Marcello Restelli
2019	B	`conf`	Exploration Driven by an Optimistic Bellman Equation. IJCNN Samuele Tosatto, Carlo D'Eramo, Joni Pajarinen, Marcello Restelli, Jan Peters
2019	B	`conf`	Feature Selection via Mutual Information: New Theoretical Insights. IJCNN Mario Beraha, Alberto Maria Metelli, Matteo Papini, Andrea Tirinzoni, Marcello Restelli
2019	J	`jnl`	Feature Selection via Mutual Information: New Theoretical Insights. CoRR Mario Beraha, Alberto Maria Metelli, Matteo Papini, Andrea Tirinzoni, Marcello Restelli
2019	J	`jnl`	Gradient-Aware Model-based Policy Search. CoRR Pierluca D'Oro, Alberto Maria Metelli, Andrea Tirinzoni, Matteo Papini, Marcello Restelli
2019	A*	`conf`	Optimistic Policy Optimization via Multiple Importance Sampling. ICML Matteo Papini, Alberto Maria Metelli, Lorenzo Lupo, Marcello Restelli
2019	J	`jnl`	Policy Space Identification in Configurable Environments. CoRR Alberto Maria Metelli, Guglielmo Manneschi, Marcello Restelli
2019	A*	`conf`	Propagating Uncertainty in Reinforcement Learning via Wasserstein Barycenters. NeurIPS Alberto Maria Metelli, Amarildo Likmeta, Marcello Restelli
2019	A*	`conf`	Reinforcement Learning in Configurable Continuous Environments. ICML Alberto Maria Metelli, Emanuele Ghelfi, Marcello Restelli
2019	J	`jnl`	Risk-Averse Trust Region Optimization for Reward-Volatility Reduction. CoRR Lorenzo Bisi, Luca Sabbioni, Edoardo Vittori, Matteo Papini, Marcello Restelli
2019	J	`jnl`	Smoothing Policies and Safe Policy Gradients. CoRR Matteo Papini, Matteo Pirotta, Marcello Restelli
2019	A*	`conf`	Transfer of Samples in Policy Search via Multiple Importance Sampling. ICML Andrea Tirinzoni, Mattia Salvini, Marcello Restelli
2018	A*	`conf`	A Combinatorial-Bandit Algorithm for the Online Joint Bid/Budget Optimization of Pay-per-Click Advertising Campaigns. AAAI Alessandro Nuara, Francesco Trovò, Nicola Gatti, Marcello Restelli
2018	A*	`conf`	Configurable Markov Decision Processes. ICML Alberto Maria Metelli, Mirco Mutti, Marcello Restelli
2018	J	`jnl`	Configurable Markov Decision Processes. CoRR Alberto Maria Metelli, Mirco Mutti, Marcello Restelli
2018	—	`conf`	Does Reinforcement Learning outperform PID in the control of FES-induced elbow flex-extension? MeMeA Davide Di Febbo, Emilia Ambrosini, Matteo Pirotta, Eric Rojas, Marcello Restelli, Alessandra Laura Giulia Pedrocchi, Simona Ferrante
2018	A*	`conf`	Importance Weighted Transfer of Samples in Reinforcement Learning. ICML Andrea Tirinzoni, Andrea Sessa, Matteo Pirotta, Marcello Restelli
2018	J	`jnl`	Importance Weighted Transfer of Samples in Reinforcement Learning. CoRR Andrea Tirinzoni, Andrea Sessa, Matteo Pirotta, Marcello Restelli
2018	J	`jnl`	Improving multi-armed bandit algorithms in online pricing settings. Int. J. Approx. Reason. Francesco Trovò, Stefano Paladino, Marcello Restelli, Nicola Gatti
2018	A*	`conf`	Policy Optimization via Importance Sampling. NeurIPS Alberto Maria Metelli, Matteo Papini, Francesco Faccio, Marcello Restelli
2018	J	`jnl`	Policy Optimization via Importance Sampling. CoRR Alberto Maria Metelli, Matteo Papini, Francesco Faccio, Marcello Restelli
2018	A*	`conf`	Stochastic Variance-Reduced Policy Gradient. ICML Matteo Papini, Damiano Binaghi, Giuseppe Canonaco, Matteo Pirotta, Marcello Restelli
2018	J	`jnl`	Stochastic Variance-Reduced Policy Gradient. CoRR Matteo Papini, Damiano Binaghi, Giuseppe Canonaco, Matteo Pirotta, Marcello Restelli
2018	B	`conf`	Targeting Optimization for Internet Advertising by Learning from Logged Bandit Feedback. IJCNN Margherita Gasparini, Alessandro Nuara, Francesco Trovò, Nicola Gatti, Marcello Restelli
2018	A*	`conf`	Transfer of Value Functions via Variational Methods. NeurIPS Andrea Tirinzoni, Rafael Rodríguez-Sánchez, Marcello Restelli
2017	—	`conf`	Adaptive Batch Size for Safe Policy Gradients. NIPS Matteo Papini, Matteo Pirotta, Marcello Restelli
2017	A*	`conf`	Boosted Fitted Q-Iteration. ICML Samuele Tosatto, Matteo Pirotta, Carlo D'Eramo, Marcello Restelli
2017	—	`conf`	Compatible Reward Inverse Reinforcement Learning. NIPS Alberto Maria Metelli, Matteo Pirotta, Marcello Restelli
2017	J	`jnl`	Cost-Sensitive Approach to Batch Size Adaptation for Gradient Descent. CoRR Matteo Pirotta, Marcello Restelli
2017	A	`conf`	Designing Learning Algorithms over the Sequence Form of an Extensive-Form Game. AAMAS Edoardo Manino, Nicola Gatti, Marcello Restelli
2017	A*	`conf`	Estimating the Maximum Expected Value in Continuous Reinforcement Learning Problems. AAAI Carlo D'Eramo, Alessandro Nuara, Matteo Pirotta, Marcello Restelli
2017	—	`conf`	Exploiting structure and uncertainty of Bellman updates in Markov decision processes. SSCI Davide Tateo, Carlo D'Eramo, Alessandro Nuara, Marcello Restelli, Andrea Bonarini
2017	—	`conf`	Gradient-based minimization for multi-expert Inverse Reinforcement Learning. SSCI Davide Tateo, Matteo Pirotta, Marcello Restelli, Andrea Bonarini
2017	A	`conf`	Regret Minimization Algorithms for the Followers Behaviour Identification in Leadership Games. UAI Lorenzo Bisi, Giuseppe De Nittis, Francesco Trovò, Marcello Restelli, Nicola Gatti
2017	B	`conf`	Risk-averse trees for learning from logged bandit feedback. IJCNN Francesco Trovò, Stefano Paladino, Paolo Simone, Marcello Restelli, Nicola Gatti
2017	A*	`conf`	Unimodal Thompson Sampling for Graph-Structured Arms. AAAI Stefano Paladino, Francesco Trovò, Marcello Restelli, Nicola Gatti
2017	—	`conf`	User context estimation for public travel assistance and intelligent service scheduling. ITSC Alessio Pagani, Francesco Bruschi, Vincenzo Rana, Marcello Restelli
2016	A	`conf`	Budgeted Multi-Armed Bandit in Continuous Action Space. ECAI Francesco Trovò, Stefano Paladino, Marcello Restelli, Nicola Gatti
2016	A*	`conf`	Estimating Maximum Expected Value through Gaussian Approximation. ICML Carlo D'Eramo, Marcello Restelli, Alessandro Nuara
2016	J	`jnl`	Extensive-form games with heterogeneous populations: solution concepts, equilibria characterization, learning dynamics. Intelligenza Artificiale Nicola Gatti, Fabio Panozzo, Marcello Restelli
2016	A*	`conf`	Inverse Reinforcement Learning through Policy Gradient Minimization. AAAI Matteo Pirotta, Marcello Restelli
2016	J	`jnl`	Multi-objective Reinforcement Learning through Continuous Pareto Manifold Approximation. J. Artif. Intell. Res. Simone Parisi, Matteo Pirotta, Marcello Restelli
2016	J	`jnl`	Policy Search for the Optimal Control of Markov Decision Processes: A Novel Particle-Based Iterative Scheme. IEEE Trans. Cybern. Giorgio Manganini, Matteo Pirotta, Marcello Restelli, Luigi Piroddi, Maria Prandini
2016	—	`conf`	Reconstruction of public transport state. ITSC Alessio Pagani, Francesco Bruschi, Vincenzo Rana, Marcello Restelli
2016	A*	`conf`	Sequence-Form and Evolutionary Dynamics: Realization Equivalence to Agent Form and Logit Dynamics. AAAI Nicola Gatti, Marcello Restelli
2016	J	`jnl`	Unimodal Thompson Sampling for Graph-Structured Arms. CoRR Stefano Paladino, Francesco Trovò, Marcello Restelli, Nicola Gatti
2015	A*	`conf`	Estimating a Mean-Path from a set of 2-D curves. ICRA Amir M. Ghalamzan E., Luca Bascetta, Marcello Restelli, Paolo Rocco
2015	B	`conf`	Following Newton direction in Policy Gradient with parameter exploration. IJCNN Giorgio Manganini, Matteo Pirotta, Marcello Restelli, Luca Bascetta
2015	A*	`conf`	Multi-Objective Reinforcement Learning with Continuous Pareto Frontier Approximation. AAAI Matteo Pirotta, Simone Parisi, Marcello Restelli
2015	J	`jnl`	Policy gradient in Lipschitz Markov Decision Processes. Mach. Learn. Matteo Pirotta, Marcello Restelli, Luca Bascetta
2015	J	`jnl`	Sparse multi-task reinforcement learning. Intelligenza Artificiale Daniele Calandriello, Alessandro Lazaric, Marcello Restelli
2014	A*	`conf`	Evolutionary Dynamics of Q-Learning over the Sequence Form. AAAI Fabio Panozzo, Nicola Gatti, Marcello Restelli
2014	J	`jnl`	Multi-objective Reinforcement Learning with Continuous Pareto Frontier Approximation. CoRR Matteo Pirotta, Simone Parisi, Marcello Restelli
2014	B	`conf`	Policy gradient approaches for multi-objective sequential decision making. IJCNN Simone Parisi, Matteo Pirotta, Nicola Smacchia, Luca Bascetta, Marcello Restelli
2014	—	`conf`	Policy gradient approaches for multi-objective sequential decision making: A comparison. ADPRL Simone Parisi, Matteo Pirotta, Nicola Smacchia, Luca Bascetta, Marcello Restelli
2014	—	`conf`	Sparse Multi-Task Reinforcement Learning. NIPS Daniele Calandriello, Alessandro Lazaric, Marcello Restelli
2013	—	`conf`	Adaptive Step-Size for Policy Gradient Methods. NIPS Matteo Pirotta, Marcello Restelli, Luca Bascetta
2013	A*	`conf`	Efficient Evolutionary Dynamics with Extensive-Form Games. AAAI Nicola Gatti, Fabio Panozzo, Marcello Restelli
2013	J	`jnl`	Efficient evolutionary dynamics with extensive-form games CoRR Nicola Gatti, Fabio Panozzo, Marcello Restelli
2013	A	`conf`	Extensive-form games with heterogeneous populations. AAMAS Nicola Gatti, Fabio Panozzo, Marcello Restelli
2013	—	`conf`	Safe Policy Iteration. ICML (3) Matteo Pirotta, Marcello Restelli, Alessio Pecorino, Daniele Calandriello
2012	A*	`conf`	Computing Equilibria with Two-Player Zero-Sum Continuous Stochastic Games with Switching Controller. AAAI Guido Bonomi, Nicola Gatti, Fabio Panozzo, Marcello Restelli
2012	J	`jnl`	Data-driven dynamic emulation modelling for the optimal management of environmental systems. Environ. Model. Softw. Andrea Castelletti, Stefano Galelli, Marcello Restelli, Rodolfo Soncini-Sessa
2012	B	`conf`	Tree-based Fitted Q-iteration for Multi-Objective Markov Decision problems. IJCNN Andrea Castelletti, Francesca Pianosi, Marcello Restelli
2011	A	`conf`	Equilibrium approximation in simulation-based extensive-form games. AAMAS Nicola Gatti, Marcello Restelli
2011	—	`conf`	Fitted policy search. ADPRL Martino Migliavacca, Alessio Pecorino, Matteo Pirotta, Marcello Restelli, Andrea Bonarini
2011	—	`conf`	Multi-objective fitted Q-iteration: Pareto frontier approximation in one single run. ICNSC Andrea Castelletti, Francesca Pianosi, Marcello Restelli
2011	J	`jnl`	Transfer from Multiple MDPs CoRR Alessandro Lazaric, Marcello Restelli
2011	—	`conf`	Transfer from Multiple MDPs. NIPS Alessandro Lazaric, Marcello Restelli
2011	—	`conf`	Tree-based variable selection for dimensionality reduction of large-scale control systems. ADPRL Andrea Castelletti, Stefano Galelli, Marcello Restelli, Rodolfo Soncini-Sessa
2009	—	`conf`	Batch Reinforcement Learning - An Application to a Controllable Semi-active Suspension System. ICINCO-ICSO Simone Tognetti, Marcello Restelli, Sergio M. Savaresi, Cristiano Spelta
2009	—	`conf`	Batch Reinforcement Learning for semi-active suspension control. CCA/ISIC Simone Tognetti, Sergio M. Savaresi, Cristiano Spelta, Marcello Restelli
2009	J	`jnl`	Reinforcement distribution in fuzzy Q-learning. Fuzzy Sets Syst. Andrea Bonarini, Alessandro Lazaric, Francesco Montrone, Marcello Restelli
2008	—	`conf`	Batch Reinforcement Learning for Controlling a Mobile Wheeled Pendulum Robot. IFIP AI Andrea Bonarini, Claudio Caccia, Alessandro Lazaric, Marcello Restelli
2008	—	`conf`	Improving Batch Reinforcement Learning Performance through Transfer of Samples. STAIRS Alessandro Lazaric, Marcello Restelli, Andrea Bonarini
2008	—	`conf`	On the usefulness of opponent modeling: the Kuhn Poker case study. AAMAS (3) Alessandro Lazaric, Mario Quaresimale, Marcello Restelli
2008	—	`conf`	Towards Automated Bargaining in Electronic Markets: A Partially Two-Sided Competition Model. AMEC/TADA Nicola Gatti, Alessandro Lazaric, Marcello Restelli
2008	A*	`conf`	Transfer of samples in batch reinforcement learning. ICML Alessandro Lazaric, Marcello Restelli, Andrea Bonarini
2008	—	`conf`	Transfer of task representation in reinforcement learning using policy-based proto-value functions. AAMAS (3) Eliseo Ferrante, Alessandro Lazaric, Marcello Restelli
2007	—	`conf`	Bifurcation Analysis of Reinforcement Learning Agents in the Selten's Horse Game. Adaptive Agents and Multi-Agents Systems Alessandro Lazaric, Enrique Munoz de Cote, Fabio Dercole, Marcello Restelli
2007	J	`jnl`	Learning Fuzzy Classifier Systems: Architecture and Exploration Issues. Int. J. Artif. Intell. Tools Andrea Bonarini, Matteo Matteucci, Marcello Restelli
2007	—	`conf`	Piecewise constant reinforcement learning for robotic applications. ICINCO-ICSO Andrea Bonarini, Alessandro Lazaric, Marcello Restelli
2007	J	`jnl`	Problems and solutions for anchoring in multi-robot applications. J. Intell. Fuzzy Syst. Andrea Bonarini, Matteo Matteucci, Marcello Restelli
2007	—	`conf`	Reinforcement Learning in Complex Environments Through Multiple Adaptive Partitions. AI*IA Andrea Bonarini, Alessandro Lazaric, Marcello Restelli
2007	—	`conf`	Reinforcement Learning in Continuous Action Spaces through Sequential Monte Carlo Methods. NIPS Alessandro Lazaric, Marcello Restelli, Andrea Bonarini
2006	J	`jnl`	Concepts and fuzzy models for behavior-based robotics. Int. J. Approx. Reason. Andrea Bonarini, Matteo Matteucci, Marcello Restelli
2006	—	`conf`	Incremental Skill Acquisition for Self-motivated Learning Animats. SAB Andrea Bonarini, Alessandro Lazaric, Marcello Restelli
2006	A	`conf`	Learning to cooperate in multi-agent social dilemmas. AAMAS Enrique Munoz de Cote, Alessandro Lazaric, Marcello Restelli
2005	A*	`conf`	Automatic Error Detection and Reduction for an Odometric Sensor based on Two Optical Mice. ICRA Andrea Bonarini, Matteo Matteucci, Marcello Restelli
2005	—	`conf`	MRT: Robotics Off-the-Shelf with the Modular Robotic Toolkit. PPSDR@ICRA Andrea Bonarini, Matteo Matteucci, Marcello Restelli
2005	—	`conf`	Reinforcement Distribution in Continuous State Action Space Fuzzy Q-Learning: A Novel Approach. WILF Andrea Bonarini, Francesco Montrone, Marcello Restelli
2004	A	`conf`	A kinematic-independent dead-reckoning sensor for indoor mobile robotics. IROS Andrea Bonarini, Matteo Matteucci, Marcello Restelli
2004	—	`—`	A multi-agent system for multi-agent learning. Marcello Restelli
2004	—	`conf`	Dead Reckoning for Mobile Robots Using Two Optical Mice. ICINCO (2) Andrea Bonarini, Matteo Matteucci, Marcello Restelli
2003	C	`conf`	A Probabilistic Framework for Weighting Different Sensor Data in MUREA. RoboCup Marcello Restelli, Domenico G. Sorrenti, Fabio M. Marchese
2003	—	`conf`	Concepts and Fuzzy Models for Behavior-Based Robotics. WILF Andrea Bonarini, Matteo Matteucci, Marcello Restelli
2003	C	`conf`	Filling the Gap among Coordination, Planning, and Reaction Using a Fuzzy Cognitive Model. RoboCup Andrea Bonarini, Matteo Matteucci, Marcello Restelli
2002	A	`conf`	A robot localization method based on evidence accumulation and multi-resolution. IROS Marcello Restelli, Domenico G. Sorrenti, Fabio M. Marchese
2002	A	`conf`	An architecture to implement agents co-operating in dynamic environments. AAMAS Andrea Bonarini, Marcello Restelli
2002	C	`conf`	MUREA: A MUlti-Resolution Evidence Accumulation Method for Robot Localization in Known Environments. RoboCup Marcello Restelli, Domenico G. Sorrenti, Fabio M. Marchese
2001	C	`conf`	A Framework for Robust Sensing in Multi-agent Systems. RoboCup Andrea Bonarini, Matteo Matteucci, Marcello Restelli
2001	—	`conf`	Concepts for Anchoring in Robotics. AI*IA Andrea Bonarini, Matteo Matteucci, Marcello Restelli
2001	C	`conf`	Fun2Mas: The Milan Robocup Team. RoboCup Andrea Bonarini, Giovanni Invernizzi, Fabio M. Marchese, Matteo Matteucci, Marcello Restelli, Domenico G. Sorrenti