Alert button
Picture for Matteo Papini

Matteo Papini

Alert button

Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs

Add code
Bookmark button
Alert button
May 10, 2024
Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restelli

Viaarxiv icon

Policy Gradient with Active Importance Sampling

Add code
Bookmark button
Alert button
May 09, 2024
Matteo Papini, Giorgio Manganini, Alberto Maria Metelli, Marcello Restelli

Viaarxiv icon

Learning Optimal Deterministic Policies with Stochastic Policy Gradients

Add code
Bookmark button
Alert button
May 03, 2024
Alessandro Montenegro, Marco Mussi, Alberto Maria Metelli, Matteo Papini

Viaarxiv icon

Optimisic Information Directed Sampling

Add code
Bookmark button
Alert button
Feb 23, 2024
Gergely Neu, Matteo Papini, Ludovic Schwartz

Viaarxiv icon

No-Regret Reinforcement Learning in Smooth MDPs

Add code
Bookmark button
Alert button
Feb 06, 2024
Davide Maran, Alberto Maria Metelli, Matteo Papini, Marcello Restell

Viaarxiv icon

Importance-Weighted Offline Learning Done Right

Add code
Bookmark button
Alert button
Sep 27, 2023
Germano Gabbianelli, Gergely Neu, Matteo Papini

Viaarxiv icon

Offline Primal-Dual Reinforcement Learning for Linear MDPs

Add code
Bookmark button
Alert button
May 22, 2023
Germano Gabbianelli, Gergely Neu, Nneka Okolo, Matteo Papini

Figure 1 for Offline Primal-Dual Reinforcement Learning for Linear MDPs
Viaarxiv icon

Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees

Add code
Bookmark button
Alert button
Oct 24, 2022
Andrea Tirinzoni, Matteo Papini, Ahmed Touati, Alessandro Lazaric, Matteo Pirotta

Figure 1 for Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees
Figure 2 for Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees
Figure 3 for Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees
Figure 4 for Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees
Viaarxiv icon

Online Learning with Off-Policy Feedback

Add code
Bookmark button
Alert button
Jul 18, 2022
Germano Gabbianelli, Matteo Papini, Gergely Neu

Figure 1 for Online Learning with Off-Policy Feedback
Viaarxiv icon

Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits

Add code
Bookmark button
Alert button
May 27, 2022
Gergely Neu, Julia Olkhovskaya, Matteo Papini, Ludovic Schwartz

Viaarxiv icon