default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDMarcello Restelli
Person information
SPARQL queries 
🛈 Please note that only 57% of the items listed on this page have a DOI stored with their dblp record. Therefore, DOI-based queries can only provide partial results.
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2025
[i86]Alessio Russo, Alberto Maria Metelli, Marcello Restelli:
Achieving ~O(√T) Regret in Average-Reward POMDPs with Known Observation Models. CoRR abs/2501.18790 (2025)- [i85]Riccardo Zamboni, Mirco Mutti, Marcello Restelli:
Towards Principled Multi-Agent Task Agnostic Exploration. CoRR abs/2502.08365 (2025) - [i84]Riccardo Zamboni, Enrico Brunetti, Marcello Restelli:
Scalable Multi-Agent Offline Reinforcement Learning and the Role of Information. CoRR abs/2502.11260 (2025) - 2024
- [j35]Matteo Papini, Giorgio Manganini, Alberto Maria Metelli, Marcello Restelli:
Policy Gradient with Active Importance Sampling. RLJ 2: 645-675 (2024) - [j34]Riccardo Zamboni, Duilio Cirino, Marcello Restelli, Mirco Mutti:
The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough. RLJ 2: 676-692 (2024) - [j33]Gianluca Drappo, Alberto Maria Metelli, Marcello Restelli:
A Provably Efficient Option-Based Algorithm for both High-Level and Low-Level Learning. RLJ 2: 819-839 (2024) - [j32]Paolo Bonetti
, Alberto Maria Metelli, Marcello Restelli:
Interpretable linear dimensionality reduction based on bias-variance analysis. Data Min. Knowl. Discov. 38(4): 1713-1781 (2024) - [j31]Gabor Paczolay, Matteo Papini, Alberto Maria Metelli, István Á. Harmati, Marcello Restelli:
Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds. Mach. Learn. 113(9): 6475-6510 (2024) - [j30]Riccardo Poiani, Ciprian Stirbu, Alberto Maria Metelli, Marcello Restelli:
Optimizing Empty Container Repositioning and Fleet Deployment via Configurable Semi-POMDPs. IEEE Trans. Intell. Transp. Syst. 25(5): 4704-4711 (2024) - [c166]Davide Maran, Pierriccardo Olivieri, Francesco Emanuele Stradi, Giuseppe Urso, Nicola Gatti, Marcello Restelli:
Online Markov Decision Processes Configuration with Continuous Decision Space. AAAI 2024: 14315-14322 - [c165]Théo Vincent, Alberto Maria Metelli, Boris Belousov, Jan Peters, Marcello Restelli, Carlo D'Eramo:
Parameterized Projected Bellman Operator. AAAI 2024: 15402-15410 - [c164]Francesco Bacchiocchi, Gianmarco Genalti, Davide Maran, Marco Mussi, Marcello Restelli, Nicola Gatti, Alberto Maria Metelli:
Autoregressive Bandits. AISTATS 2024: 937-945 - [c163]Angelo Damiani, Gustavo Viera-López, Giorgio Manganini, Alberto Maria Metelli, Marcello Restelli:
Transfer Learning for Dynamical Systems Models via Autoencoders and GANs. ACC 2024: 8-14 - [c162]Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restelli:
Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs. COLT 2024: 3743-3774 - [c161]Julen Cestero, Marco Quartulli, Marcello Restelli:
Building Surrogate Models Using Trajectories of Agents Trained by Reinforcement Learning. ICANN (4) 2024: 340-355 - [c160]Mirco Mutti, Riccardo De Santi, Marcello Restelli, Alexander Marx, Giorgia Ramponi:
Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning. ICLR 2024 - [c159]Gianmarco Genalti, Marco Mussi, Nicola Gatti, Marcello Restelli, Matteo Castiglioni, Alberto Maria Metelli:
Graph-Triggered Rising Bandits. ICML 2024 - [c158]Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restelli:
No-Regret Reinforcement Learning in Smooth MDPs. ICML 2024 - [c157]Marco Mussi, Simone Drago, Marcello Restelli, Alberto Maria Metelli:
Factored-Reward Bandits with Intermediate Observations. ICML 2024 - [c156]Marco Mussi, Alessandro Montenegro, Francesco Trovò, Marcello Restelli, Alberto Maria Metelli:
Best Arm Identification for Stochastic Rising Bandits. ICML 2024 - [c155]Riccardo Zamboni, Duilio Cirino, Marcello Restelli, Mirco Mutti:
How to Explore with Belief: State Entropy Maximization in POMDPs. ICML 2024 - [c154]Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli:
Causal Feature Selection via Transfer Entropy. IJCNN 2024: 1-10 - [c153]Vincenzo De Paola, Giuseppe Calcagno, Alberto Maria Metelli, Marcello Restelli:
The Power of Hybrid Learning in Industrial Robotics: Efficient Grasping Strategies with Supervised-Driven Reinforcement Learning. IJCNN 2024: 1-9 - [c152]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:
A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics. NeurIPS 2024 - [c151]Davide Maran, Francesco Bacchiocchi, Francesco Emanuele Stradi, Matteo Castiglioni, Nicola Gatti, Marcello Restelli:
Bandits with Ranking Feedback. NeurIPS 2024 - [c150]Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restelli:
Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs. NeurIPS 2024 - [c149]Riccardo Poiani, Gabriele Curti, Alberto Maria Metelli, Marcello Restelli:
Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning. NeurIPS 2024 - [c148]Riccardo Poiani, Rémy Degenne, Emilie Kaufmann, Alberto Maria Metelli, Marcello Restelli:
Optimal Multi-Fidelity Best-Arm Identification. NeurIPS 2024 - [c147]Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli:
Interpetable Target-Feature Aggregation for Multi-task Learning Based on Bias-Variance Analysis. ECML/PKDD (6) 2024: 74-91 - [i83]Riccardo Poiani, Gabriele Curti, Alberto Maria Metelli, Marcello Restelli:
Inverse Reinforcement Learning with Sub-optimal Experts. CoRR abs/2401.03857 (2024) - [i82]Carlo D'Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters:
Sharing Knowledge in Multi-Task Deep Reinforcement Learning. CoRR abs/2401.09561 (2024) - [i81]Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restelli:
No-Regret Reinforcement Learning in Smooth MDPs. CoRR abs/2402.03792 (2024) - [i80]Khaled Eldowa, Nicolò Cesa-Bianchi, Alberto Maria Metelli, Marcello Restelli:
Information Capacity Regret Bounds for Bandits with Mediator Feedback. CoRR abs/2402.10282 (2024) - [i79]Matteo Papini, Giorgio Manganini, Alberto Maria Metelli, Marcello Restelli:
Policy Gradient with Active Importance Sampling. CoRR abs/2405.05630 (2024) - [i78]Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restelli:
Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs. CoRR abs/2405.06363 (2024) - [i77]Riccardo Zamboni, Duilio Cirino, Marcello Restelli, Mirco Mutti:
How to Explore with Belief: State Entropy Maximization in POMDPs. CoRR abs/2406.02295 (2024) - [i76]Riccardo Poiani, Rémy Degenne, Emilie Kaufmann, Alberto Maria Metelli, Marcello Restelli:
Optimal Multi-Fidelity Best-Arm Identification. CoRR abs/2406.03033 (2024) - [i75]Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli:
Interpetable Target-Feature Aggregation for Multi-Task Learning based on Bias-Variance Analysis. CoRR abs/2406.07991 (2024) - [i74]Riccardo Zamboni, Duilio Cirino, Marcello Restelli, Mirco Mutti:
The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough. CoRR abs/2406.12795 (2024) - [i73]Gianluca Drappo, Alberto Maria Metelli, Marcello Restelli:
A Provably Efficient Option-Based Algorithm for both High-Level and Low-Level Learning. CoRR abs/2406.15124 (2024) - [i72]Gianvito Losapio, Davide Beretta, Marco Mussi, Alberto Maria Metelli, Marcello Restelli:
State and Action Factorization in Power Grids. CoRR abs/2409.04467 (2024) - [i71]Gianmarco Genalti, Marco Mussi, Nicola Gatti, Marcello Restelli, Matteo Castiglioni, Alberto Maria Metelli:
Bridging Rested and Restless Bandits with Graph-Triggering: Rising and Rotting. CoRR abs/2409.05980 (2024) - [i70]Alessio Russo, Alberto Maria Metelli, Marcello Restelli:
Efficient Learning of POMDPs with Known Observation Model in Average-Reward Setting. CoRR abs/2410.01331 (2024) - [i69]Riccardo Poiani, Nicole Nobili, Alberto Maria Metelli, Marcello Restelli:
Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach. CoRR abs/2410.13463 (2024) - [i68]Vito Alessandro Monaco, Antonio Riva, Luca Sabbioni, Lorenzo Bisi, Edoardo Vittori, Marco Pinciroli, Michele Trapletti, Marcello Restelli:
Exploiting Risk-Aversion and Size-dependent fees in FX Trading with Fitted Natural Actor-Critic. CoRR abs/2410.23294 (2024) - [i67]Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restelli:
Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs. CoRR abs/2410.24071 (2024) - [i66]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:
A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics. CoRR abs/2411.05718 (2024) - [i65]Majid Molaei, Marcello Restelli, Alberto Maria Metelli, Matteo Papini:
Statistical Analysis of Policy Space Compression Problem. CoRR abs/2411.09900 (2024) - [i64]Davide Maran, Marcello Restelli:
A parametric algorithm is optimal for non-parametric regression of smooth functions. CoRR abs/2412.14744 (2024) - 2023
- [j29]Massimiliano Bonetti, Lorenzo Bisi, Marcello Restelli:
Risk-averse optimization of reward-based coherent risk measures. Artif. Intell. 316: 103845 (2023) - [j28]Marco Mussi, Davide Lombarda, Alberto Maria Metelli, Francesco Trovò, Marcello Restelli:
ARLO: A framework for Automated Reinforcement Learning. Expert Syst. Appl. 224: 119883 (2023) - [j27]Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, Marcello Restelli:
Convex Reinforcement Learning in Finite Trials. J. Mach. Learn. Res. 24: 250:1-250:42 (2023) - [j26]Gianluca Drappo, Alberto Maria Metelli, Marcello Restelli:
An Option-Dependent Analysis of Regret Minimization Algorithms in Finite-Horizon Semi-MDP. Trans. Mach. Learn. Res. 2023 (2023) - [j25]Filippo Fedeli, Alberto Maria Metelli, Francesco Trovò, Marcello Restelli:
IWDA: Importance Weighting for Drift Adaptation in Streaming Supervised Learning Problems. IEEE Trans. Neural Networks Learn. Syst. 34(10): 6813-6823 (2023) - [c146]Amarildo Likmeta, Matteo Sacco, Alberto Maria Metelli, Marcello Restelli:
Wasserstein Actor-Critic: Directed Exploration via Optimism for Continuous-Actions Control. AAAI 2023: 8782-8790 - [c145]Davide Maran, Alberto Maria Metelli, Marcello Restelli:
Tight Performance Guarantees of Imitator Policies with Continuous Actions. AAAI 2023: 9073-9080 - [c144]Mirco Mutti, Riccardo De Santi, Emanuele Rossi, Juan Felipe Calderón, Michael M. Bronstein, Marcello Restelli:
Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization. AAAI 2023: 9251-9259 - [c143]Luca Sabbioni, Luca Al Daire, Lorenzo Bisi, Alberto Maria Metelli, Marcello Restelli:
Simultaneously Updating All Persistence Values in Reinforcement Learning. AAAI 2023: 9668-9676 - [c142]Marco Mussi, Gianmarco Genalti, Alessandro Nuara, Francesco Trovò, Marcello Restelli, Nicola Gatti:
Dynamic Pricing with Volume Discounts in Online Settings. AAAI 2023: 15560-15568 - [c141]Alberto Maria Metelli, Mirco Mutti, Marcello Restelli:
A Tale of Sampling and Estimation in Discounted Reinforcement Learning. AISTATS 2023: 4575-4601 - [c140]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:
A Brief Guide to Multi-Objective Reinforcement Learning and Planning. AAMAS 2023: 1988-1990 - [c139]Ahmed Elmaraghy, Jacopo Montali, Marcello Restelli, Francesco Causone, Pierpaolo Ruttico:
Towards an AI-Based Framework for Autonomous Design and Construction: Learning from Reinforcement Learning Success in RTS Games. CAAD Futures 2023: 376-392 - [c138]Alberto Maria Metelli, Filippo Lazzati, Marcello Restelli:
Towards Theoretical Understanding of Inverse Reinforcement Learning. ICML 2023: 24555-24591 - [c137]Marco Mussi, Alberto Maria Metelli, Marcello Restelli:
Dynamical Linear Bandits. ICML 2023: 25563-25587 - [c136]Riccardo Poiani, Alberto Maria Metelli, Marcello Restelli:
Truncating Trajectories in Monte Carlo Reinforcement Learning. ICML 2023: 27994-28042 - [c135]Khaled Eldowa, Nicolò Cesa-Bianchi, Alberto Maria Metelli, Marcello Restelli:
Information-Theoretic Regret Bounds for Bandits with Fixed Expert Advice. ITW 2023: 30-35 - [c134]Riccardo Poiani, Nicole Nobili, Alberto Maria Metelli, Marcello Restelli:
Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach. NeurIPS 2023 - [c133]Riccardo Zamboni, Alberto Maria Metelli, Marcello Restelli:
Distributional Policy Evaluation: a Maximum Entropy approach to Representation Learning. NeurIPS 2023 - [c132]Luca Sabbioni, Francesco Corda, Marcello Restelli:
Stepsize Learning for Policy Gradient Methods in Contextual Markov Decision Processes. ECML/PKDD (4) 2023: 506-523 - [c131]Alberto Maria Metelli, Samuele Meta, Marcello Restelli:
On the Relation between Policy Improvement and Off-Policy Minimum-Variance Policy Evaluation. UAI 2023: 1423-1433 - [i63]Marco Mussi, Alessandro Montenegro, Francesco Trovò, Marcello Restelli, Alberto Maria Metelli:
Best Arm Identification for Stochastic Rising Bandits. CoRR abs/2302.07510 (2023) - [i62]Amarildo Likmeta, Matteo Sacco, Alberto Maria Metelli, Marcello Restelli:
Wasserstein Actor-Critic: Directed Exploration via Optimism for Continuous-Actions Control. CoRR abs/2303.02378 (2023) - [i61]Khaled Eldowa, Nicolò Cesa-Bianchi, Alberto Maria Metelli, Marcello Restelli:
Information-Theoretic Regret Bounds for Bandits with Fixed Expert Advice. CoRR abs/2303.08102 (2023) - [i60]Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli:
Interpretable Linear Dimensionality Reduction based on Bias-Variance Analysis. CoRR abs/2303.14734 (2023) - [i59]Alberto Maria Metelli, Mirco Mutti, Marcello Restelli:
A Tale of Sampling and Estimation in Discounted Reinforcement Learning. CoRR abs/2304.05073 (2023) - [i58]Alberto Maria Metelli, Filippo Lazzati, Marcello Restelli:
Towards Theoretical Understanding of Inverse Reinforcement Learning. CoRR abs/2304.12966 (2023) - [i57]Riccardo Poiani, Alberto Maria Metelli, Marcello Restelli:
Truncating Trajectories in Monte Carlo Reinforcement Learning. CoRR abs/2305.04361 (2023) - [i56]Gianluca Drappo, Alberto Maria Metelli, Marcello Restelli:
An Option-Dependent Analysis of Regret Minimization Algorithms in Finite-Horizon Semi-Markov Decision Processes. CoRR abs/2305.06936 (2023) - [i55]Luca Sabbioni, Francesco Corda, Marcello Restelli:
Stepsize Learning for Policy Gradient Methods in Contextual Markov Decision Processes. CoRR abs/2306.07741 (2023) - [i54]Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli:
Nonlinear Feature Aggregation: Two Algorithms driven by Theory. CoRR abs/2306.11143 (2023) - [i53]Riccardo Poiani, Alberto Maria Metelli, Marcello Restelli:
Pure Exploration under Mediators' Feedback. CoRR abs/2308.15552 (2023) - [i52]Mirco Mutti, Riccardo De Santi, Marcello Restelli, Alexander Marx, Giorgia Ramponi:
Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning. CoRR abs/2310.07518 (2023) - [i51]Paolo Bonetti, Alberto Maria Metelli, Marcello Restelli:
Causal Feature Selection via Transfer Entropy. CoRR abs/2310.11059 (2023) - [i50]Théo Vincent, Alberto Maria Metelli, Boris Belousov, Jan Peters, Marcello Restelli, Carlo D'Eramo:
Parameterized Projected Bellman Operator. CoRR abs/2312.12869 (2023) - 2022
- [j24]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:
A practical guide to multi-objective reinforcement learning and planning. Auton. Agents Multi Agent Syst. 36(1): 26 (2022) - [j23]Alessandro Nuara, Francesco Trovò, Nicola Gatti, Marcello Restelli:
Online joint bid/daily budget optimization of Internet advertising campaigns. Artif. Intell. 305: 103663 (2022) - [j22]Lorenzo Bisi, Davide Santambrogio, Federico Sandrelli, Andrea Tirinzoni, Brian D. Ziebart, Marcello Restelli:
Risk-averse policy optimization via risk-neutral policy optimization. Artif. Intell. 311: 103765 (2022) - [j21]Alberto Maria Metelli, Guglielmo Manneschi, Marcello Restelli:
Policy space identification in configurable environments. Mach. Learn. 111(6): 2093-2145 (2022) - [j20]Matteo Papini, Matteo Pirotta, Marcello Restelli:
Smoothing policies and safe policy gradients. Mach. Learn. 111(11): 4081-4137 (2022) - [c130]Pierre Liotet, Francesco Vidaich, Alberto Maria Metelli, Marcello Restelli:
Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization. AAAI 2022: 7525-7533 - [c129]Mirco Mutti, Mattia Mancassola, Marcello Restelli:
Unsupervised Reinforcement Learning in Multiple Environments. AAAI 2022: 7850-7858 - [c128]Mirco Mutti, Stefano Del Col, Marcello Restelli:
Reward-Free Policy Space Compression for Reinforcement Learning. AISTATS 2022: 3187-3203 - [c127]Khaled Eldowa, Lorenzo Bisi, Marcello Restelli:
Finite Sample Analysis of Mean-Volatility Actor-Critic for Risk-Averse Reinforcement Learning. AISTATS 2022: 10028-10066 - [c126]Manuel Occorso, Luca Sabbioni, Alberto Maria Metelli, Marcello Restelli:
Trust Region Meta Learning for Policy Optimization. Meta-Knowledge Transfer @ ECML/PKDD 2022: 62-74 - [c125]Martino Bernasconi, Stefano Martino, Edoardo Vittori, Francesco Trovò, Marcello Restelli:
Dark-Pool Smart Order Routing: a Combinatorial Multi-armed Bandit Approach. ICAIF 2022: 352-360 - [c124]Antonio Riva, Lorenzo Bisi, Pierre Liotet, Luca Sabbioni, Edoardo Vittori, Marco Pinciroli, Michele Trapletti, Marcello Restelli:
Addressing Non-Stationarity in FX Trading with Online Model Selection of Offline RL Experts. ICAIF 2022: 394-402 - [c123]Lorenzo Moro, Amarildo Likmeta, Enrico Prati, Marcello Restelli:
Goal-Directed Planning via Hindsight Experience Replay. ICLR 2022 - [c122]Angelo Damiani, Giorgio Manganini, Alberto Maria Metelli, Marcello Restelli:
Balancing Sample Efficiency and Suboptimality in Inverse Reinforcement Learning. ICML 2022: 4618-4629 - [c121]Pierre Liotet, Davide Maran, Lorenzo Bisi, Marcello Restelli:
Delayed Reinforcement Learning by Imitation. ICML 2022: 13528-13556 - [c120]Alberto Maria Metelli, Francesco Trovò, Matteo Pirola, Marcello Restelli:
Stochastic Rising Bandits. ICML 2022: 15421-15457 - [c119]Mirco Mutti, Riccardo De Santi, Marcello Restelli:
The Importance of Non-Markovianity in Maximum State Entropy Exploration. ICML 2022: 16223-16239 - [c118]Giulia Romano, Andrea Agostini, Francesco Trovò, Nicola Gatti, Marcello Restelli:
Multi-Armed Bandit Problem with Temporally-Partitioned Rewards: When Partial Feedback Counts. IJCAI 2022: 3401-3407 - [c117]Julen Cestero, Marco Quartulli, Alberto Maria Metelli, Marcello Restelli:
Storehouse: a Reinforcement Learning Environment for Optimizing Warehouse Management. IJCNN 2022: 1-9 - [c116]Marco Mussi, Gianmarco Genalti, Francesco Trovò, Alessandro Nuara, Nicola Gatti, Marcello Restelli:
Pricing the Long Tail by Explainable Product Aggregation and Monotonic Bandits. KDD 2022: 3623-3633 - [c115]Nicolò Felicioni, Maurizio Ferrari Dacrema, Marcello Restelli, Paolo Cremonesi:
Off-Policy Evaluation with Deficient Support Using Side Information. NeurIPS 2022 - [c114]Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, Marcello Restelli:
Challenging Common Assumptions in Convex Reinforcement Learning. NeurIPS 2022 - [c113]Riccardo Poiani, Alberto Maria Metelli, Marcello Restelli:
Multi-Fidelity Best-Arm Identification. NeurIPS 2022 - [c112]Giorgia Ramponi, Marcello Restelli:
Learning in Markov games: Can we exploit a general-sum opponent? UAI 2022: 1665-1675 - [i49]Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, Marcello Restelli:
Challenging Common Assumptions in Convex Reinforcement Learning. CoRR abs/2202.01511 (2022) - [i48]Mirco Mutti, Riccardo De Santi, Marcello Restelli:
The Importance of Non-Markovianity in Maximum State Entropy Exploration. CoRR abs/2202.03060 (2022) - [i47]Mirco Mutti, Riccardo De Santi, Emanuele Rossi, Juan Felipe Calderón, Michael M. Bronstein, Marcello Restelli:
Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization. CoRR abs/2202.06545 (2022) - [i46]Mirco Mutti, Stefano Del Col, Marcello Restelli:
Reward-Free Policy Space Compression for Reinforcement Learning. CoRR abs/2202.11079 (2022) - [i45]Pierre Liotet, Davide Maran, Lorenzo Bisi, Marcello Restelli:
Delayed Reinforcement Learning by Imitation. CoRR abs/2205.05569 (2022) - [i44]Marco Mussi, Davide Lombarda, Alberto Maria Metelli, Francesco Trovò, Marcello Restelli:
ARLO: A Framework for Automated Reinforcement Learning. CoRR abs/2205.10416 (2022) - [i43]Giulia Romano, Andrea Agostini, Francesco Trovò, Nicola Gatti, Marcello Restelli:
Multi-Armed Bandit Problem with Temporally-Partitioned Rewards: When Partial Feedback Counts. CoRR abs/2206.00586 (2022) - [i42]Julen Cestero, Marco Quartulli, Alberto Maria Metelli, Marcello Restelli:
Storehouse: a Reinforcement Learning Environment for Optimizing Warehouse Management. CoRR abs/2207.03851 (2022) - [i41]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:
Analysis, Characterization, Prediction and Attribution of Extreme Atmospheric Events with Machine Learning: a Review. CoRR abs/2207.07580 (2022) - [i40]Riccardo Poiani, Ciprian Stirbu, Alberto Maria Metelli, Marcello Restelli:
Optimizing Empty Container Repositioning and Fleet Deployment via Configurable Semi-POMDPs. CoRR abs/2207.12509 (2022) - [i39]Marco Mussi, Alberto Maria Metelli, Marcello Restelli:
Dynamical Linear Bandits. CoRR abs/2211.08997 (2022) - [i38]Marco Mussi, Gianmarco Genalti, Alessandro Nuara, Francesco Trovò, Marcello Restelli, Nicola Gatti:
Dynamic Pricing with Volume Discounts in Online Settings. CoRR abs/2211.09612 (2022) - [i37]Luca Sabbioni, Luca Al Daire, Lorenzo Bisi, Alberto Maria Metelli, Marcello Restelli:
Simultaneously Updating All Persistence Values in Reinforcement Learning. CoRR abs/2211.11620 (2022) - [i36]Alberto Maria Metelli, Francesco Trovò, Matteo Pirola, Marcello Restelli:
Stochastic Rising Bandits. CoRR abs/2212.03798 (2022) - [i35]Davide Maran, Alberto Maria Metelli, Marcello Restelli:
Tight Performance Guarantees of Imitator Policies with Continuous Actions. CoRR abs/2212.03922 (2022) - [i34]Francesco Bacchiocchi, Gianmarco Genalti, Davide Maran, Marco Mussi, Marcello Restelli, Nicola Gatti, Alberto Maria Metelli:
Autoregressive Bandits. CoRR abs/2212.06251 (2022) - 2021
- [j19]Alberto Maria Metelli, Matteo Pirotta, Daniele Calandriello, Marcello Restelli:
Safe Policy Iteration: A Monotonically Improving Approximate Policy Iteration Approach. J. Mach. Learn. Res. 22: 97:1-97:83 (2021) - [j18]Carlo D'Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters:
MushroomRL: Simplifying Reinforcement Learning Research. J. Mach. Learn. Res. 22: 131:1-131:5 (2021) - [j17]Carlo D'Eramo, Andrea Cini, Alessandro Nuara, Matteo Pirotta, Cesare Alippi, Jan Peters, Marcello Restelli:
Gaussian Approximation for Bias Reduction in Q-Learning. J. Mach. Learn. Res. 22: 277:1-277:51 (2021) - [j16]Amarildo Likmeta, Alberto Maria Metelli, Giorgia Ramponi, Andrea Tirinzoni, Matteo Giuliani, Marcello Restelli:
Dealing with multiple experts and non-stationarity in inverse reinforcement learning: an application to real-life problems. Mach. Learn. 110(9): 2541-2576 (2021) - [c111]Alberto Maria Metelli, Matteo Papini, Pierluca D'Oro, Marcello Restelli:
Policy Optimization as Online Learning with Mediator Feedback. AAAI 2021: 8958-8966 - [c110]Mirco Mutti, Lorenzo Pratissoli, Marcello Restelli:
Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate. AAAI 2021: 9028-9036 - [c109]Giorgia Ramponi, Marcello Restelli:
Newton Optimization on Helmholtz Decomposition for Continuous Games. AAAI 2021: 11325-11333 - [c108]Edoardo Vittori, Amarildo Likmeta, Marcello Restelli:
Monte carlo tree search for trading and hedging. ICAIF 2021: 37:1-37:9 - [c107]Antonio Riva, Lorenzo Bisi, Pierre Liotet, Luca Sabbioni, Edoardo Vittori, Marco Pinciroli, Michele Trapletti, Marcello Restelli:
Learning FX trading strategies with FQI and persistent actions. ICAIF 2021: 38:1-38:9 - [c106]Alberto Maria Metelli, Giorgia Ramponi, Alessandro Concetti, Marcello Restelli:
Provably Efficient Learning of Transferable Rewards. ICML 2021: 7665-7676 - [c105]Matteo Papini, Andrea Tirinzoni, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta:
Leveraging Good Representations in Linear Contextual Bandits. ICML 2021: 8371-8380 - [c104]Riccardo Poiani, Andrea Tirinzoni, Marcello Restelli:
Meta-Reinforcement Learning by Tracking Task Non-stationarity. IJCAI 2021: 2899-2905 - [c103]Pierre Liotet, Erick Venneri, Marcello Restelli:
Learning a Belief Representation for Delayed Reinforcement Learning. IJCNN 2021: 1-8 - [c102]Alberto Maria Metelli, Alessio Russo, Marcello Restelli:
Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and Learning. NeurIPS 2021: 8119-8132 - [c101]Matteo Papini, Andrea Tirinzoni, Aldo Pacchiano, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta:
Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection. NeurIPS 2021: 16371-16383 - [c100]Giorgia Ramponi, Alberto Maria Metelli, Alessandro Concetti, Marcello Restelli:
Learning in Non-Cooperative Configurable Markov Decision Processes. NeurIPS 2021: 22808-22821 - [c99]Martino Bernasconi de Luca, Edoardo Vittori, Francesco Trovò, Marcello Restelli:
Conservative Online Convex Optimization. ECML/PKDD (1) 2021: 19-34 - [c98]Gerlando Re, Fabio Chiusano, Francesco Trovò, Diego Carrera, Giacomo Boracchi, Marcello Restelli:
Exploiting History Data for Nonstationary Multi-armed Bandit. ECML/PKDD (1) 2021: 51-66 - [c97]Giuseppe Canonaco, Andrea Soprani, Matteo Giuliani, Andrea Castelletti, Manuel Roveri, Marcello Restelli:
Time-variant variational transfer for value functions. UAI 2021: 876-886 - [i33]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:
A Practical Guide to Multi-Objective Reinforcement Learning and Planning. CoRR abs/2103.09568 (2021) - [i32]Matteo Papini, Andrea Tirinzoni, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta:
Leveraging Good Representations in Linear Contextual Bandits. CoRR abs/2104.03781 (2021) - [i31]Riccardo Poiani, Andrea Tirinzoni, Marcello Restelli:
Meta-Reinforcement Learning by Tracking Task Non-stationarity. CoRR abs/2105.08834 (2021) - [i30]Matteo Papini, Andrea Tirinzoni, Aldo Pacchiano, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta:
Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection. CoRR abs/2110.14798 (2021) - [i29]Pierre Liotet, Francesco Vidaich, Alberto Maria Metelli, Marcello Restelli:
Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization. CoRR abs/2112.06625 (2021) - [i28]Mirco Mutti, Mattia Mancassola, Marcello Restelli:
Unsupervised Reinforcement Learning in Multiple Environments. CoRR abs/2112.08746 (2021) - 2020
- [j15]Alberto Maria Metelli, Matteo Pirotta, Marcello Restelli:
On the use of the policy gradient and Hessian in inverse reinforcement learning. Intelligenza Artificiale 14(1): 117-150 (2020) - [j14]Francesco Trovò, Marcello Restelli, Nicola Gatti:
Sliding-Window Thompson Sampling for Non-Stationary Settings. J. Artif. Intell. Res. 68: 311-364 (2020) - [j13]Alberto Maria Metelli, Matteo Papini, Nico Montali, Marcello Restelli:
Importance Sampling Techniques for Policy Optimization. J. Mach. Learn. Res. 21: 141:1-141:75 (2020) - [j12]Amarildo Likmeta, Alberto Maria Metelli, Andrea Tirinzoni, Riccardo Giol, Marcello Restelli, Danilo Romano:
Combining reinforcement learning with rule-based controllers for transparent and general decision-making in autonomous driving. Robotics Auton. Syst. 131: 103568 (2020) - [c96]Pierluca D'Oro, Alberto Maria Metelli, Andrea Tirinzoni, Matteo Papini, Marcello Restelli:
Gradient-Aware Model-Based Policy Search. AAAI 2020: 3801-3808 - [c95]Mirco Mutti, Marcello Restelli:
An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies. AAAI 2020: 5232-5239 - [c94]Matteo Papini, Andrea Battistello, Marcello Restelli:
Balancing Learning Speed and Stability in Policy Gradient via Adaptive Exploration. AISTATS 2020: 1188-1199 - [c93]Giorgia Ramponi, Amarildo Likmeta, Alberto Maria Metelli, Andrea Tirinzoni, Marcello Restelli:
Truly Batch Model-Free Inverse Reinforcement Learning about Multiple Intentions. AISTATS 2020: 2359-2369 - [c92]Andrea Tirinzoni, Alessandro Lazaric, Marcello Restelli:
A Novel Confidence-Based Algorithm for Structured Bandits. AISTATS 2020: 3175-3185 - [c91]Alessandro Nuara, Francesco Trovò, Dominic Crippa, Nicola Gatti, Marcello Restelli:
Driving Exploration by Maximum Distribution in Gaussian Process Bandits. AAMAS 2020: 948-956 - [c90]Giuseppe Canonaco, Marcello Restelli, Manuel Roveri:
Model-Free Non-Stationarity Detection and Adaptation in Reinforcement Learning. ECAI 2020: 1047-1054 - [c89]Luca Sabbioni, Marcello Restelli, Andrea Prampolini:
Fast direct calibration of interest rate derivatives pricing models. ICAIF 2020: 6:1-6:8 - [c88]Edoardo Vittori, Martino Bernasconi de Luca, Francesco Trovò, Marcello Restelli:
Dealing with transaction costs in portfolio optimization: online gradient descent with momentum. ICAIF 2020: 11:1-11:8 - [c87]Lorenzo Bisi, Pierre Liotet, Luca Sabbioni, Gianmarco Reho, Nico Montali, Marcello Restelli, Cristiana Corno:
Foreign exchange trading: a risk-averse batch reinforcement learning approach. ICAIF 2020: 26:1-26:8 - [c86]Edoardo Vittori, Michele Trapletti, Marcello Restelli:
Option hedging with risk averse reinforcement learning. ICAIF 2020: 27:1-27:8 - [c85]Carlo D'Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters:
Sharing Knowledge in Multi-Task Deep Reinforcement Learning. ICLR 2020 - [c84]Alberto Maria Metelli, Flavio Mazzolini, Lorenzo Bisi, Luca Sabbioni, Marcello Restelli:
Control Frequency Adaptation via Action Persistence in Batch Reinforcement Learning. ICML 2020: 6862-6873 - [c83]Andrea Tirinzoni, Riccardo Poiani, Marcello Restelli:
Sequential Transfer in Reinforcement Learning with a Generative Model. ICML 2020: 9481-9492 - [c82]Andrea Schillaci, Maurizio Quadrio, Carlotta Pipolo, Marcello Restelli, Giacomo Boracchi:
Inferring Functional Properties from Fluid Dynamics Features. ICPR 2020: 4091-4098 - [c81]Lorenzo Bisi, Luca Sabbioni, Edoardo Vittori, Matteo Papini, Marcello Restelli:
Risk-Averse Trust Region Optimization for Reward-Volatility Reduction. IJCAI 2020: 4583-4589 - [c80]Giorgia Ramponi, Gianluca Drappo, Marcello Restelli:
Inverse Reinforcement Learning from a Gradient-based Learner. NeurIPS 2020 - [c79]Andrea Tirinzoni, Matteo Pirotta, Marcello Restelli, Alessandro Lazaric:
An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits. NeurIPS 2020 - [i27]Carlo D'Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters:
MushroomRL: Simplifying Reinforcement Learning Research. CoRR abs/2001.01102 (2020) - [i26]Alberto Maria Metelli, Flavio Mazzolini, Lorenzo Bisi, Luca Sabbioni, Marcello Restelli:
Control Frequency Adaptation via Action Persistence in Batch Reinforcement Learning. CoRR abs/2002.06836 (2020) - [i25]Alessandro Nuara, Francesco Trovò, Nicola Gatti, Marcello Restelli:
Online Joint Bid/Daily Budget Optimization of Internet Advertising Campaigns. CoRR abs/2003.01452 (2020) - [i24]Andrea Tirinzoni, Alessandro Lazaric, Marcello Restelli:
A Novel Confidence-Based Algorithm for Structured Bandits. CoRR abs/2005.11593 (2020) - [i23]Giuseppe Canonaco, Andrea Soprani, Manuel Roveri, Marcello Restelli:
Time-Variant Variational Transfer for Value Functions. CoRR abs/2005.12864 (2020) - [i22]Andrea Tirinzoni, Riccardo Poiani, Marcello Restelli:
Sequential Transfer in Reinforcement Learning with a Generative Model. CoRR abs/2007.00722 (2020) - [i21]Mirco Mutti, Lorenzo Pratissoli, Marcello Restelli:
A Policy Gradient Method for Task-Agnostic Exploration. CoRR abs/2007.04640 (2020) - [i20]Giorgia Ramponi, Marcello Restelli:
Newton-based Policy Optimization for Games. CoRR abs/2007.07804 (2020) - [i19]Giorgia Ramponi, Gianluca Drappo, Marcello Restelli:
Inverse Reinforcement Learning from a Gradient-based Learner. CoRR abs/2007.07812 (2020) - [i18]Edoardo Vittori, Michele Trapletti, Marcello Restelli:
Option Hedging with Risk Averse Reinforcement Learning. CoRR abs/2010.12245 (2020) - [i17]Andrea Tirinzoni, Matteo Pirotta, Marcello Restelli, Alessandro Lazaric:
An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits. CoRR abs/2010.12247 (2020) - [i16]Alberto Maria Metelli, Matteo Papini, Pierluca D'Oro, Marcello Restelli:
Policy Optimization as Online Learning with Mediator Feedback. CoRR abs/2012.08225 (2020)
2010 – 2019
- 2019
- [c78]Alberto Maria Metelli, Emanuele Ghelfi, Marcello Restelli:
Reinforcement Learning in Configurable Continuous Environments. ICML 2019: 4546-4555 - [c77]Matteo Papini, Alberto Maria Metelli, Lorenzo Lupo, Marcello Restelli:
Optimistic Policy Optimization via Multiple Importance Sampling. ICML 2019: 4989-4999 - [c76]Andrea Tirinzoni, Mattia Salvini, Marcello Restelli:
Transfer of Samples in Policy Search via Multiple Importance Sampling. ICML 2019: 6264-6274 - [c75]Mario Beraha, Alberto Maria Metelli, Matteo Papini, Andrea Tirinzoni, Marcello Restelli:
Feature Selection via Mutual Information: New Theoretical Insights. IJCNN 2019: 1-9 - [c74]Carlo D'Eramo, Andrea Cini, Marcello Restelli:
Exploiting Action-Value Uncertainty to Drive Exploration in Reinforcement Learning. IJCNN 2019: 1-8 - [c73]Samuele Tosatto, Carlo D'Eramo, Joni Pajarinen, Marcello Restelli, Jan Peters:
Exploration Driven by an Optimistic Bellman Equation. IJCNN 2019: 1-8 - [c72]Alberto Maria Metelli, Amarildo Likmeta, Marcello Restelli:
Propagating Uncertainty in Reinforcement Learning via Wasserstein Barycenters. NeurIPS 2019: 4335-4347 - [c71]Alessandro Nuara, Nicola Sosio, Francesco Trovò, Maria Chiara Zaccardi, Nicola Gatti, Marcello Restelli:
Dealing with Interdependencies and Uncertainty in Multi-Channel Advertising Campaigns Optimization. WWW 2019: 1376-1386 - [i15]Matteo Papini, Matteo Pirotta, Marcello Restelli:
Smoothing Policies and Safe Policy Gradients. CoRR abs/1905.03231 (2019) - [i14]Mirco Mutti, Marcello Restelli:
An Intrinsically-Motivated Approach for Learning Highly Exploring and Fast Mixing Policies. CoRR abs/1907.04662 (2019) - [i13]Mario Beraha, Alberto Maria Metelli, Matteo Papini, Andrea Tirinzoni, Marcello Restelli:
Feature Selection via Mutual Information: New Theoretical Insights. CoRR abs/1907.07384 (2019) - [i12]Alberto Maria Metelli, Guglielmo Manneschi, Marcello Restelli:
Policy Space Identification in Configurable Environments. CoRR abs/1909.03984 (2019) - [i11]Pierluca D'Oro, Alberto Maria Metelli, Andrea Tirinzoni, Matteo Papini, Marcello Restelli:
Gradient-Aware Model-based Policy Search. CoRR abs/1909.04115 (2019) - [i10]Lorenzo Bisi, Luca Sabbioni, Edoardo Vittori, Matteo Papini, Marcello Restelli:
Risk-Averse Trust Region Optimization for Reward-Volatility Reduction. CoRR abs/1912.03193 (2019) - 2018
- [j11]Francesco Trovò, Stefano Paladino, Marcello Restelli, Nicola Gatti:
Improving multi-armed bandit algorithms in online pricing settings. Int. J. Approx. Reason. 98: 196-235 (2018) - [c70]Alessandro Nuara, Francesco Trovò, Nicola Gatti, Marcello Restelli:
A Combinatorial-Bandit Algorithm for the Online Joint Bid/Budget Optimization of Pay-per-Click Advertising Campaigns. AAAI 2018: 2379-2386 - [c69]Alberto Maria Metelli, Mirco Mutti, Marcello Restelli:
Configurable Markov Decision Processes. ICML 2018: 3488-3497 - [c68]Matteo Papini, Damiano Binaghi, Giuseppe Canonaco, Matteo Pirotta, Marcello Restelli:
Stochastic Variance-Reduced Policy Gradient. ICML 2018: 4023-4032 - [c67]Andrea Tirinzoni, Andrea Sessa, Matteo Pirotta, Marcello Restelli:
Importance Weighted Transfer of Samples in Reinforcement Learning. ICML 2018: 4943-4952 - [c66]Margherita Gasparini, Alessandro Nuara, Francesco Trovò, Nicola Gatti, Marcello Restelli:
Targeting Optimization for Internet Advertising by Learning from Logged Bandit Feedback. IJCNN 2018: 1-8 - [c65]Davide Di Febbo, Emilia Ambrosini, Matteo Pirotta, Eric Rojas, Marcello Restelli, Alessandra Laura Giulia Pedrocchi, Simona Ferrante:
Does Reinforcement Learning outperform PID in the control of FES-induced elbow flex-extension? MeMeA 2018: 1-6 - [c64]Alberto Maria Metelli, Matteo Papini, Francesco Faccio, Marcello Restelli:
Policy Optimization via Importance Sampling. NeurIPS 2018: 5447-5459 - [c63]Andrea Tirinzoni, Rafael Rodríguez-Sánchez, Marcello Restelli:
Transfer of Value Functions via Variational Methods. NeurIPS 2018: 6182-6192 - [i9]Andrea Tirinzoni, Andrea Sessa, Matteo Pirotta, Marcello Restelli:
Importance Weighted Transfer of Samples in Reinforcement Learning. CoRR abs/1805.10886 (2018) - [i8]Alberto Maria Metelli, Mirco Mutti, Marcello Restelli:
Configurable Markov Decision Processes. CoRR abs/1806.05415 (2018) - [i7]Matteo Papini, Damiano Binaghi, Giuseppe Canonaco, Matteo Pirotta, Marcello Restelli:
Stochastic Variance-Reduced Policy Gradient. CoRR abs/1806.05618 (2018) - [i6]Alberto Maria Metelli, Matteo Papini, Francesco Faccio, Marcello Restelli:
Policy Optimization via Importance Sampling. CoRR abs/1809.06098 (2018) - 2017
- [c62]Carlo D'Eramo, Alessandro Nuara, Matteo Pirotta, Marcello Restelli:
Estimating the Maximum Expected Value in Continuous Reinforcement Learning Problems. AAAI 2017: 1840-1846 - [c61]Stefano Paladino, Francesco Trovò, Marcello Restelli, Nicola Gatti:
Unimodal Thompson Sampling for Graph-Structured Arms. AAAI 2017: 2457-2463 - [c60]Edoardo Manino, Nicola Gatti, Marcello Restelli:
Designing Learning Algorithms over the Sequence Form of an Extensive-Form Game. AAMAS 2017: 1622-1624 - [c59]Samuele Tosatto, Matteo Pirotta, Carlo D'Eramo, Marcello Restelli:
Boosted Fitted Q-Iteration. ICML 2017: 3434-3443 - [c58]Francesco Trovò, Stefano Paladino, Paolo Simone, Marcello Restelli, Nicola Gatti:
Risk-averse trees for learning from logged bandit feedback. IJCNN 2017: 976-983 - [c57]Alessio Pagani, Francesco Bruschi, Vincenzo Rana, Marcello Restelli:
User context estimation for public travel assistance and intelligent service scheduling. ITSC 2017: 1-8 - [c56]Alberto Maria Metelli, Matteo Pirotta, Marcello Restelli:
Compatible Reward Inverse Reinforcement Learning. NIPS 2017: 2050-2059 - [c55]Matteo Papini, Matteo Pirotta, Marcello Restelli:
Adaptive Batch Size for Safe Policy Gradients. NIPS 2017: 3591-3600 - [c54]Davide Tateo, Carlo D'Eramo, Alessandro Nuara, Marcello Restelli, Andrea Bonarini:
Exploiting structure and uncertainty of Bellman updates in Markov decision processes. SSCI 2017: 1-8 - [c53]Davide Tateo, Matteo Pirotta, Marcello Restelli, Andrea Bonarini:
Gradient-based minimization for multi-expert Inverse Reinforcement Learning. SSCI 2017: 1-8 - [c52]Lorenzo Bisi, Giuseppe De Nittis, Francesco Trovò, Marcello Restelli, Nicola Gatti:
Regret Minimization Algorithms for the Followers Behaviour Identification in Leadership Games. UAI 2017 - [i5]Matteo Pirotta, Marcello Restelli:
Cost-Sensitive Approach to Batch Size Adaptation for Gradient Descent. CoRR abs/1712.03428 (2017) - 2016
- [j10]Nicola Gatti, Fabio Panozzo, Marcello Restelli:
Extensive-form games with heterogeneous populations: solution concepts, equilibria characterization, learning dynamics. Intelligenza Artificiale 10(1): 19-31 (2016) - [j9]Simone Parisi, Matteo Pirotta, Marcello Restelli:
Multi-objective Reinforcement Learning through Continuous Pareto Manifold Approximation. J. Artif. Intell. Res. 57: 187-227 (2016) - [j8]Giorgio Manganini, Matteo Pirotta, Marcello Restelli, Luigi Piroddi, Maria Prandini:
Policy Search for the Optimal Control of Markov Decision Processes: A Novel Particle-Based Iterative Scheme. IEEE Trans. Cybern. 46(11): 2643-2655 (2016) - [c51]Nicola Gatti, Marcello Restelli:
Sequence-Form and Evolutionary Dynamics: Realization Equivalence to Agent Form and Logit Dynamics. AAAI 2016: 509-515 - [c50]Matteo Pirotta, Marcello Restelli:
Inverse Reinforcement Learning through Policy Gradient Minimization. AAAI 2016: 1993-1999 - [c49]Francesco Trovò, Stefano Paladino, Marcello Restelli, Nicola Gatti:
Budgeted Multi-Armed Bandit in Continuous Action Space. ECAI 2016: 560-568 - [c48]Carlo D'Eramo, Marcello Restelli, Alessandro Nuara:
Estimating Maximum Expected Value through Gaussian Approximation. ICML 2016: 1032-1040 - [c47]Alessio Pagani, Francesco Bruschi, Vincenzo Rana, Marcello Restelli:
Reconstruction of public transport state. ITSC 2016: 2285-2292 - [i4]Stefano Paladino, Francesco Trovò, Marcello Restelli, Nicola Gatti:
Unimodal Thompson Sampling for Graph-Structured Arms. CoRR abs/1611.05724 (2016) - 2015
- [j7]Daniele Calandriello, Alessandro Lazaric, Marcello Restelli:
Sparse multi-task reinforcement learning. Intelligenza Artificiale 9(1): 5-20 (2015) - [j6]Matteo Pirotta, Marcello Restelli, Luca Bascetta:
Policy gradient in Lipschitz Markov Decision Processes. Mach. Learn. 100(2-3): 255-283 (2015) - [c46]Matteo Pirotta, Simone Parisi, Marcello Restelli:
Multi-Objective Reinforcement Learning with Continuous Pareto Frontier Approximation. AAAI 2015: 2928-2934 - [c45]Amir M. Ghalamzan E., Luca Bascetta, Marcello Restelli, Paolo Rocco:
Estimating a Mean-Path from a set of 2-D curves. ICRA 2015: 2048-2053 - [c44]Giorgio Manganini, Matteo Pirotta, Marcello Restelli, Luca Bascetta:
Following Newton direction in Policy Gradient with parameter exploration. IJCNN 2015: 1-8 - 2014
- [c43]Fabio Panozzo, Nicola Gatti, Marcello Restelli:
Evolutionary Dynamics of Q-Learning over the Sequence Form. AAAI 2014: 2034-2040 - [c42]Simone Parisi, Matteo Pirotta, Nicola Smacchia, Luca Bascetta, Marcello Restelli:
Policy gradient approaches for multi-objective sequential decision making: A comparison. ADPRL 2014: 1-8 - [c41]Simone Parisi, Matteo Pirotta, Nicola Smacchia, Luca Bascetta, Marcello Restelli:
Policy gradient approaches for multi-objective sequential decision making. IJCNN 2014: 2323-2330 - [c40]Daniele Calandriello, Alessandro Lazaric, Marcello Restelli:
Sparse Multi-Task Reinforcement Learning. NIPS 2014: 819-827 - [i3]Matteo Pirotta, Simone Parisi, Marcello Restelli:
Multi-objective Reinforcement Learning with Continuous Pareto Frontier Approximation. CoRR abs/1406.3497 (2014) - 2013
- [c39]Nicola Gatti, Fabio Panozzo, Marcello Restelli:
Efficient Evolutionary Dynamics with Extensive-Form Games. AAAI 2013: 335-341 - [c38]Nicola Gatti, Fabio Panozzo, Marcello Restelli:
Extensive-form games with heterogeneous populations. AAMAS 2013: 1199-1200 - [c37]Matteo Pirotta, Marcello Restelli, Alessio Pecorino, Daniele Calandriello:
Safe Policy Iteration. ICML (3) 2013: 307-315 - [c36]Matteo Pirotta, Marcello Restelli, Luca Bascetta:
Adaptive Step-Size for Policy Gradient Methods. NIPS 2013: 1394-1402 - [i2]Nicola Gatti, Fabio Panozzo, Marcello Restelli:
Efficient evolutionary dynamics with extensive-form games. CoRR abs/1304.1456 (2013) - 2012
- [j5]Andrea Castelletti, Stefano Galelli, Marcello Restelli, Rodolfo Soncini-Sessa:
Data-driven dynamic emulation modelling for the optimal management of environmental systems. Environ. Model. Softw. 34: 30-43 (2012) - [c35]Guido Bonomi, Nicola Gatti, Fabio Panozzo, Marcello Restelli:
Computing Equilibria with Two-Player Zero-Sum Continuous Stochastic Games with Switching Controller. AAAI 2012: 1270-1277 - [c34]Andrea Castelletti, Francesca Pianosi, Marcello Restelli:
Tree-based Fitted Q-iteration for Multi-Objective Markov Decision problems. IJCNN 2012: 1-8 - 2011
- [c33]Andrea Castelletti, Stefano Galelli, Marcello Restelli, Rodolfo Soncini-Sessa:
Tree-based variable selection for dimensionality reduction of large-scale control systems. ADPRL 2011: 62-69 - [c32]Martino Migliavacca, Alessio Pecorino, Matteo Pirotta, Marcello Restelli, Andrea Bonarini:
Fitted policy search. ADPRL 2011: 287-294 - [c31]Nicola Gatti, Marcello Restelli:
Equilibrium approximation in simulation-based extensive-form games. AAMAS 2011: 199-206 - [c30]Andrea Castelletti, Francesca Pianosi, Marcello Restelli:
Multi-objective fitted Q-iteration: Pareto frontier approximation in one single run. ICNSC 2011: 260-265 - [c29]Alessandro Lazaric, Marcello Restelli:
Transfer from Multiple MDPs. NIPS 2011: 1746-1754 - [i1]Alessandro Lazaric, Marcello Restelli:
Transfer from Multiple MDPs. CoRR abs/1108.6211 (2011)
2000 – 2009
- 2009
- [j4]Andrea Bonarini, Alessandro Lazaric, Francesco Montrone, Marcello Restelli:
Reinforcement distribution in fuzzy Q-learning. Fuzzy Sets Syst. 160(10): 1420-1443 (2009) - [c28]Simone Tognetti, Sergio M. Savaresi, Cristiano Spelta, Marcello Restelli:
Batch Reinforcement Learning for semi-active suspension control. CCA/ISIC 2009: 582-587 - [c27]Simone Tognetti, Marcello Restelli, Sergio M. Savaresi, Cristiano Spelta:
Batch Reinforcement Learning - An Application to a Controllable Semi-active Suspension System. ICINCO-ICSO 2009: 228-233 - 2008
- [c26]Nicola Gatti, Alessandro Lazaric, Marcello Restelli:
Towards Automated Bargaining in Electronic Markets: A Partially Two-Sided Competition Model. AMEC/TADA 2008: 117-130 - [c25]Eliseo Ferrante, Alessandro Lazaric, Marcello Restelli:
Transfer of task representation in reinforcement learning using policy-based proto-value functions. AAMAS (3) 2008: 1329-1332 - [c24]Alessandro Lazaric, Mario Quaresimale, Marcello Restelli:
On the usefulness of opponent modeling: the Kuhn Poker case study. AAMAS (3) 2008: 1345-1348 - [c23]Alessandro Lazaric, Marcello Restelli, Andrea Bonarini:
Transfer of samples in batch reinforcement learning. ICML 2008: 544-551 - [c22]Andrea Bonarini, Claudio Caccia, Alessandro Lazaric, Marcello Restelli:
Batch Reinforcement Learning for Controlling a Mobile Wheeled Pendulum Robot. IFIP AI 2008: 151-160 - [c21]Alessandro Lazaric, Marcello Restelli, Andrea Bonarini:
Improving Batch Reinforcement Learning Performance through Transfer of Samples. STAIRS 2008: 106-117 - 2007
- [j3]Andrea Bonarini, Matteo Matteucci, Marcello Restelli:
Learning Fuzzy Classifier Systems: Architecture and Exploration Issues. Int. J. Artif. Intell. Tools 16(2): 269-289 (2007) - [j2]Andrea Bonarini, Matteo Matteucci, Marcello Restelli:
Problems and solutions for anchoring in multi-robot applications. J. Intell. Fuzzy Syst. 18(3): 245-254 (2007) - [c20]Alessandro Lazaric, Enrique Munoz de Cote, Fabio Dercole, Marcello Restelli:
Bifurcation Analysis of Reinforcement Learning Agents in the Selten's Horse Game. Adaptive Agents and Multi-Agents Systems 2007: 129-144 - [c19]Andrea Bonarini, Alessandro Lazaric, Marcello Restelli:
Reinforcement Learning in Complex Environments Through Multiple Adaptive Partitions. AI*IA 2007: 531-542 - [c18]Andrea Bonarini, Alessandro Lazaric, Marcello Restelli:
Piecewise constant reinforcement learning for robotic applications. ICINCO-ICSO 2007: 214-221 - [c17]Alessandro Lazaric, Marcello Restelli, Andrea Bonarini:
Reinforcement Learning in Continuous Action Spaces through Sequential Monte Carlo Methods. NIPS 2007: 833-840 - 2006
- [j1]Andrea Bonarini, Matteo Matteucci, Marcello Restelli:
Concepts and fuzzy models for behavior-based robotics. Int. J. Approx. Reason. 41(2): 110-127 (2006) - [c16]Enrique Munoz de Cote, Alessandro Lazaric, Marcello Restelli:
Learning to cooperate in multi-agent social dilemmas. AAMAS 2006: 783-785 - [c15]Andrea Bonarini, Alessandro Lazaric, Marcello Restelli:
Incremental Skill Acquisition for Self-motivated Learning Animats. SAB 2006: 357-368 - 2005
- [c14]Andrea Bonarini, Matteo Matteucci, Marcello Restelli:
MRT: Robotics Off-the-Shelf with the Modular Robotic Toolkit. PPSDR@ICRA 2005: 345-364 - [c13]Andrea Bonarini, Matteo Matteucci, Marcello Restelli:
Automatic Error Detection and Reduction for an Odometric Sensor based on Two Optical Mice. ICRA 2005: 1675-1680 - [c12]Andrea Bonarini, Francesco Montrone, Marcello Restelli:
Reinforcement Distribution in Continuous State Action Space Fuzzy Q-Learning: A Novel Approach. WILF 2005: 40-45 - 2004
- [b1]Marcello Restelli:
A multi-agent system for multi-agent learning. Polytechnic University of Milan, Italy, 2004 - [c11]Andrea Bonarini, Matteo Matteucci, Marcello Restelli:
Dead Reckoning for Mobile Robots Using Two Optical Mice. ICINCO (2) 2004: 87-94 - [c10]Andrea Bonarini, Matteo Matteucci, Marcello Restelli:
A kinematic-independent dead-reckoning sensor for indoor mobile robotics. IROS 2004: 3750-3755 - 2003
- [c9]Andrea Bonarini, Matteo Matteucci, Marcello Restelli:
Filling the Gap among Coordination, Planning, and Reaction Using a Fuzzy Cognitive Model. RoboCup 2003: 662-669 - [c8]Marcello Restelli, Domenico G. Sorrenti, Fabio M. Marchese:
A Probabilistic Framework for Weighting Different Sensor Data in MUREA. RoboCup 2003: 678-685 - [c7]Andrea Bonarini, Matteo Matteucci, Marcello Restelli:
Concepts and Fuzzy Models for Behavior-Based Robotics. WILF 2003: 72-79 - 2002
- [c6]Andrea Bonarini, Marcello Restelli:
An architecture to implement agents co-operating in dynamic environments. AAMAS 2002: 1143-1144 - [c5]Marcello Restelli, Domenico G. Sorrenti, Fabio M. Marchese:
A robot localization method based on evidence accumulation and multi-resolution. IROS 2002: 415-420 - [c4]Marcello Restelli, Domenico G. Sorrenti, Fabio M. Marchese:
MUREA: A MUlti-Resolution Evidence Accumulation Method for Robot Localization in Known Environments. RoboCup 2002: 351-358 - 2001
- [c3]Andrea Bonarini, Matteo Matteucci, Marcello Restelli:
Concepts for Anchoring in Robotics. AI*IA 2001: 327-332 - [c2]Andrea Bonarini, Matteo Matteucci, Marcello Restelli:
A Framework for Robust Sensing in Multi-agent Systems. RoboCup 2001: 287-292 - [c1]Andrea Bonarini, Giovanni Invernizzi, Fabio M. Marchese, Matteo Matteucci, Marcello Restelli, Domenico G. Sorrenti:
Fun2Mas: The Milan Robocup Team. RoboCup 2001: 639-642
Coauthor Index
[i86] [j35] [j33] [j32] [j31] [j30] [c165] [c164] [c163] [c162] [c159] [c158] [c157] [c156] [c154] [c153] [c150] [c149] [c148] [c147] [i83] [i81] [i80] [i79] [i78] [i76] [i75] [i73] [i72] [i71] [i70] [i69] [i67] [i65] [j28] [j26] [j25] [c146] [c145] [c143] [c141] [c138] [c137] [c136] [c135] [c134] [c133] [c131] [i63] [i62] [i61] [i60] [i59] [i58] [i57] [i56] [i54] [i53] [i51] [i50] [j21] [c130] [c126] [c122] [c120] [c117] [c113] [i44] [i42] [i40] [i39] [i37] [i36] [i35] [i34] [j19] [j16] [c111] [c106] [c102] [c100] [i29] [j15] [j13] [j12] [c96] [c93] [c84] [i26] [i16] [c78] [c77] [c75] [c72] [i13] [i12] [i11] [c69] [c64] [i8] [i6] [c56]
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2025-03-27 23:31 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
