PAPINI, MATTEO
PAPINI, MATTEO
DIPARTIMENTO DI ELETTRONICA, INFORMAZIONE E BIOINGEGNERIA
Adaptive Batch Size for Safe Policy Gradients
2017-01-01 Papini, Matteo; Pirotta, M.; Restelli, M.
Balancing Learning Speed and Stability in Policy Gradient via Adaptive Exploration
2020-01-01 Papini, M.; Battistello, A.; Restelli, M.
Feature Selection via Mutual Information: New Theoretical Insights
2019-01-01 Beraha, M.; Metelli, A. M.; Papini, M.; Tirinzoni, A.; Restelli, M.
Gradient-Aware Model-Based Policy Search
2020-01-01 D'Oro, Pierluca; Metelli, ALBERTO MARIA; Tirinzoni, Andrea; Papini, Matteo; Restelli, Marcello
Importance Sampling Techniques for Policy Optimization
2020-01-01 Metelli, ALBERTO MARIA; Papini, Matteo; Montali, Nico; Restelli, Marcello
Learning Optimal Deterministic Policies with Stochastic Policy Gradients
2024-01-01 Montenegro, Alessandro; Mussi, Marco; Metelli, ALBERTO MARIA; Papini, Matteo
Leveraging Good Representations in Linear Contextual Bandits
2021-01-01 Papini, Matteo; Tirinzoni, Andrea; Restelli, Marcello; Lazaric, Alessandro; Pirotta, Matteo
Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits
2022-01-01 Neu, G.; Papini, M.; Olkhovskaya, J.; Schwartz, L.
Online Learning with Off-Policy Feedback
2023-01-01 Gabbianelli, G.; Neu, G.; Papini, M.
Optimistic Policy Optimization via Multiple Importance Sampling
2019-01-01 Papini, Matteo; Metelli, Alberto Maria; Lupo, Lorenzo; Restelli, Marcello
Policy Optimization as Online Learning with Mediator Feedback
2021-01-01 Metelli, ALBERTO MARIA; Papini, Matteo; D'Oro, Pierluca; Restelli, Marcello
Policy optimization via importance sampling
2018-01-01 Metelli, A. M.; Papini, M.; Faccio, F.; Restelli, M.
Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection
2021-01-01 Papini, Matteo; Tirinzoni, Andrea; Pacchiano, Aldo; Restelli, Marcello; Lazaric, Alessandro; Pirotta, Matteo
Risk-Averse Trust Region Optimization for Reward-Volatility Reduction
2020-01-01 Bisi, L.; Sabbioni, L.; Vittori, E.; Papini, M.; Restelli, M.
Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds
2024-01-01 Paczolay, Gabor; Papini, Matteo; Metelli, Alberto Maria; Harmati, Istvan; Restelli, Marcello
Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees
2022-01-01 Tirinzoni, A.; Papini, M.; Touati, A.; Lazaric, A.; Pirotta, M.
Smoothing policies and safe policy gradients
2022-01-01 Papini, M.; Pirotta, M.; Restelli, M.
Stochastic Variance-Reduced Policy Gradient
2018-01-01 Papini, Matteo; Binaghi, Damiano; Canonaco, Giuseppe; Pirotta, Matteo; Restelli, Marcello