Matteo Pirotta

发表

Fitted Policy Search: Direct Policy Search using a Batch Reinforcement Learning Approach

Andrea Bonarini, Marcello Restelli, Martino Migliavacca, 2010 .

Local Differentially Private Regret Minimization in Reinforcement Learning pdf

Vianney Perchet, Matteo Pirotta, Evrard Garcelon, 2020, ArXiv.

Importance Weighted Transfer of Samples in Reinforcement Learning pdf

Marcello Restelli, Matteo Pirotta, Andrea Tirinzoni, 2018, ICML.

Frequentist Regret Bounds for Randomized Least-Squares Value Iteration

Alessandro Lazaric, Matteo Pirotta, David Brandfonbrener, 2019, AISTATS.

Policy gradient in Lipschitz Markov Decision Processes

Luca Bascetta, Marcello Restelli, Matteo Pirotta, 2015, Machine Learning.

A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces pdf

Michal Valko, Matteo Pirotta, Emilie Kaufmann, 2020, ArXiv.

Conservative Exploration in Reinforcement Learning pdf

Alessandro Lazaric, Mohammad Ghavamzadeh, Matteo Pirotta, 2020, AISTATS.

An upper limb Functional Electrical Stimulation controller based on Reinforcement Learning: A feasibility case study.

Marcello Restelli, Alessandra Pedrocchi, Emilia Ambrosini, 2018 .

A Provably Efficient Sample Collection Strategy for Reinforcement Learning pdf

Alessandro Lazaric, Michal Valko, Matteo Pirotta, 2020, ArXiv.

Exploration-Exploitation in Constrained MDPs pdf

Shie Mannor, Matteo Pirotta, Yonathan Efroni, 2020, ArXiv.

Improved Algorithms for Conservative Exploration in Bandits pdf

Alessandro Lazaric, Mohammad Ghavamzadeh, Matteo Pirotta, 2020, AAAI.

Adaptive Step-Size for Policy Gradient Methods

Luca Bascetta, Marcello Restelli, Matteo Pirotta, 2013, NIPS.

Stochastic Variance-Reduced Policy Gradient

Marcello Restelli, Matteo Pirotta, Matteo Papini, 2018, ICML.

Cost-Sensitive Approach to Batch Size Adaptation for Gradient Descent pdf

Marcello Restelli, Matteo Pirotta, Matteo Pirotta, 2017, ArXiv.

Adversarial Attacks on Linear Contextual Bandits pdf

Olivier Teytaud, Alessandro Lazaric, Matteo Pirotta, 2020, NeurIPS.

Estimating the Maximum Expected Value in Continuous Reinforcement Learning Problems

Marcello Restelli, Carlo D'Eramo, Alessandro Nuara, 2017, AAAI.

Compatible Reward Inverse Reinforcement Learning

Marcello Restelli, Matteo Pirotta, Alberto Maria Metelli, 2017, NIPS.

Multi-Objective Reinforcement Learning with Continuous Pareto Frontier Approximation

Marcello Restelli, Simone Parisi, Matteo Pirotta, 2014, AAAI.

Regret Minimization in MDPs with Options without Prior Knowledge

Alessandro Lazaric, Emma Brunskill, Matteo Pirotta, 2017, NIPS.

Improved Analysis of UCRL2 with Empirical Bernstein Inequality pdf

Alessandro Lazaric, Matteo Pirotta, Ronan Fruit, 2020, ArXiv.

2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2014, Orlando, FL, USA, December 9-12, 2014

Luca Bascetta, Simone Parisi, Petar Kormushev, 2014, ADPRL.

Smoothing policies and safe policy gradients pdf

Marcello Restelli, Matteo Pirotta, Matteo Papini, 2019, Machine Learning.

On the use of the policy gradient and Hessian in inverse reinforcement learning

Marcello Restelli, Matteo Pirotta, Alberto Maria Metelli, 2020, Intelligenza Artificiale.

Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning

Alessandro Lazaric, Ronald Ortner, Matteo Pirotta, 2018, ICML.

Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes

Alessandro Lazaric, Matteo Pirotta, Ronan Fruit, 2018, NeurIPS.

Exploration Bonus for Regret Minimization in Undiscounted Discrete and Continuous Markov Decision Processes pdf

Alessandro Lazaric, Matteo Pirotta, Ronan Fruit, 2018, ArXiv.

Learning Adaptive Exploration Strategies in Dynamic Environments Through Informed Policy Regularization pdf

Ludovic Denoyer, Alessandro Lazaric, Nicolas Usunier, 2020, ArXiv.

Multi-objective Reinforcement Learning through Continuous Pareto Manifold Approximation

Marcello Restelli, Simone Parisi, Matteo Pirotta, 2016, J. Artif. Intell. Res..

Policy Search for the Optimal Control of Markov Decision Processes: A Novel Particle-Based Iterative Scheme

Luigi Piroddi, Marcello Restelli, Maria Prandini, 2016, IEEE Transactions on Cybernetics.

An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits pdf

Alessandro Lazaric, Marcello Restelli, Matteo Pirotta, 2020, NeurIPS.

Exploration Bonus for Regret Minimization in Discrete and Continuous Average Reward MDPs

Alessandro Lazaric, Matteo Pirotta, Ronan Fruit, 2019, NeurIPS.

Optimal control to reduce emissions in gasoline engines: an iterative learning control approach for ECU calibration maps improvement

Alessandro Falsone, Danilo Caporale, Luca Deori, 2015, 2015 European Control Conference (ECC).

Exploiting Language Instructions for Interpretable and Compositional Reinforcement Learning pdf

Elia Bruni, Matteo Pirotta, Michiel van der Meer, 2020, ArXiv.

Regret Bounds for Learning State Representations in Reinforcement Learning

Alessandro Lazaric, Ronald Ortner, Matteo Pirotta, 2019, NeurIPS.

Robotics - Localization & Bayesian Filtering

Matteo Pirotta, 2013 .

Improved Sample Complexity for Incremental Autonomous Exploration in MDPs pdf

Alessandro Lazaric, Michal Valko, Matteo Pirotta, 2020, NeurIPS.

Adaptive Batch Size for Safe Policy Gradients

Marcello Restelli, Matteo Pirotta, Matteo Papini, 2017, NIPS.

Following Newton direction in Policy Gradient with parameter exploration

Luca Bascetta, Marcello Restelli, Matteo Pirotta, 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

Manifold-based multi-objective policy search with sample reuse

Jan Peters, Simone Parisi, Matteo Pirotta, 2017, Neurocomputing.

Regret Bounds for Kernel-Based Reinforcement Learning pdf

Michal Valko, Matteo Pirotta, Emilie Kaufmann, 2020, ArXiv.

Policy gradient approaches for multi-objective sequential decision making: A comparison

Luca Bascetta, Marcello Restelli, Simone Parisi, 2014, 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL).

No-Regret Exploration in Goal-Oriented Reinforcement Learning

Alessandro Lazaric, Michal Valko, Matteo Pirotta, 2019, ICML.

Safe Policy Iteration

Daniele Calandriello, Marcello Restelli, Alessio Pecorino, 2013, ICML.

Concentration Inequalities for Multinoulli Random Variables pdf

Alessandro Lazaric, Matteo Pirotta, Ronan Fruit, 2020, ArXiv.

Gradient-based minimization for multi-expert Inverse Reinforcement Learning

Andrea Bonarini, Marcello Restelli, Matteo Pirotta, 2017, 2017 IEEE Symposium Series on Computational Intelligence (SSCI).

Policy gradient approaches for multi-objective sequential decision making

Luca Bascetta, Marcello Restelli, Simone Parisi, 2014, 2014 International Joint Conference on Neural Networks (IJCNN).

Boosted Fitted Q-Iteration

Marcello Restelli, Carlo D'Eramo, Matteo Pirotta, 2017, ICML.

Inverse Reinforcement Learning through Policy Gradient Minimization

Marcello Restelli, Matteo Pirotta, Matteo Pirotta, 2016, AAAI.

Does Reinforcement Learning outperform PID in the control of FES-induced elbow flex-extension?

Marcello Restelli, Simona Ferrante, Matteo Pirotta, 2018, 2018 IEEE International Symposium on Medical Measurements and Applications (MeMeA).

Active Model Estimation in Markov Decision Processes

Alessandro Lazaric, Mohammad Ghavamzadeh, Matteo Pirotta, 2020, UAI.

Fitted policy search

Andrea Bonarini, Marcello Restelli, Martino Migliavacca, 2011, 2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL).

Adaptive Multi-Goal Exploration pdf

Alessandro Lazaric, Michal Valko, Matteo Pirotta, 2021, ArXiv.

Differentially Private Exploration in Reinforcement Learning with Linear Representation pdf

Alessandro Lazaric, Matteo Pirotta, Paul Luyo, 2021, ArXiv.

Homomorphically Encrypted Linear Contextual Bandit pdf

Vianney Perchet, Matteo Pirotta, Evrard Garcelon, 2021, ArXiv.

Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret pdf

Alessandro Lazaric, Simon S. Du, Matteo Pirotta, 2021, NeurIPS.

A Unified Framework for Conservative Exploration pdf

Alessandro Lazaric, Liwei Wang, Simon S. Du, 2021, ArXiv.

Kernel-Based Reinforcement Learning: A Finite-Time Analysis

Michal Valko, Matteo Pirotta, Emilie Kaufmann, 2021, ICML.

Privacy Amplification via Shuffling for Linear Contextual Bandits pdf

Vianney Perchet, Kamalika Chaudhuri, Matteo Pirotta, 2021, ALT.

Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection pdf

Alessandro Lazaric, Marcello Restelli, Aldo Pacchiano, 2021, NeurIPS.

A Fully Problem-Dependent Regret Lower Bound for Finite-Horizon MDPs pdf

Alessandro Lazaric, Matteo Pirotta, Andrea Tirinzoni, 2021, ArXiv.

Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model

Alessandro Lazaric, Matteo Pirotta, Jean Tarbouriech, 2021, ALT.

Leveraging Good Representations in Linear Contextual Bandits

Alessandro Lazaric, Marcello Restelli, Matteo Pirotta, 2021, ICML.

No-Regret Exploration in Goal-Oriented Reinforcement Learning

Alessandro Lazaric, Michal Valko, Matteo Pirotta, 2020, ICML.

Frequentist Regret Bounds for Randomized Least-Squares Value Iteration

Alessandro Lazaric, Matteo Pirotta, David Brandfonbrener, 2020, AISTATS.