Matteo Papini

Matteo Papini

Auto-generated profile, based on publicly available information

Matteo Papini

Politecnico di Milano Milan Italy

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2019
Verified
Conference Paper
Closed access
MBMario Beraha
Mario Beraha
AMAlberto Maria Metelli
Alberto Maria Metelli
MPMatteo Papini
Matteo Papini
ATAndrea Tirinzoni
Andrea Tirinzoni
MRMarcello Restelli
Marcello Restelli
Mutual information has been successfully adopted in filter feature-selection methods to assess both the relevancy of a subset of features in predicting the target variable and the redundancy with respect to other variables. However, existing algorithms are mostly heuristic and do not offer any guarantee on the proposed solution. In this paper, we provide novel theoretical results showing that conditional mutual information naturally arises when bounding the ideal regression/classification errors achieved by different subsets of features. Leveraging on these insights, we propose a novel stopping condition for backward and forward greedy methods which ensures that the ideal prediction error using the selected feature subset remains bounded by a user-specified threshold. We provide numerical simulations to support our theoretical claims and compare to common heuristic methods.

20 October 2022 in Machine Learning
Verified
Journal Article
Open access
PDF file
MPMatteo Papini
Matteo Papini
MPMatteo Pirotta
Matteo Pirotta
MRMarcello Restelli
Marcello Restelli
Policy gradient (PG) algorithms are among the best candidates for the much-anticipated applications of reinforcement learning to real-world control tasks, such as robotics. However, the trial-and-error nature of these methods poses safety issues whenever the learning process itself must be performed on a physical system or involves any form of human-computer interaction. In this paper, we address a specific safety formulation, where both goals and dangers are encoded in a scalar reward signal and the learning agent is constrained to never worsen its performance, measured as the expected sum of rewards. By studying actor-only PG from a stochastic optimization perspective, we establish improvement guarantees for a wide class of parametric policies, generalizing existing results on Gaussian policies. This, together with novel upper bounds on the variance of PG estimators, allows us to identify meta-parameter schedules that guarantee monotonic improvement with high probability. The two key meta-parameters are the step size of the parameter updates and the batch size of the gradient estimates. Through a joint, adaptive selection of these meta-parameters, we obtain a PG algorithm with monotonic improvement guarantees.

27 June 2024 in Machine Learning
Verified
Journal Article
Closed access
PDF file
GPGabor Paczolay
Gabor Paczolay
MPMatteo Papini
Matteo Papini
AMAlberto Maria Metelli
Alberto Maria Metelli
IHIstvan Harmati
Istvan Harmati
MRMarcello Restelli
Marcello Restelli

11 July 2025 in Machine Learning
Verified
Journal Article
Closed access
PDF file
GTGianmarco Tedeschi
Gianmarco Tedeschi
MPMatteo Papini
Matteo Papini
AMAlberto Maria Metelli
Alberto Maria Metelli
MRMarcello Restelli
Marcello Restelli

22 May 2023 in arXiv
Verified
Preprint
Open access
PDF file
GGGermano Gabbianelli
Germano Gabbianelli
GNGergely Neu
Gergely Neu
NONneka Okolo
Nneka Okolo
MPMatteo Papini
Matteo Papini
Offline Reinforcement Learning (RL) aims to learn a near-optimal policy from a fixed dataset of transitions collected by another policy. This problem has attracted a lot of attention recently, but most existing methods with strong theoretical guarantees are restricted to finite-horizon or tabular settings. In constrast, few algorithms for infinite-horizon settings with function approximation and minimal assumptions on the dataset are both sample and computationally efficient. Another gap in the current literature is the lack of theoretical analysis for the average-reward setting, which is more challenging than the discounted setting. In this paper, we address both of these issues by proposing a primal-dual optimization method based on the linear programming formulation of RL. Our key contribution is a new reparametrization that allows us to derive low-variance gradient estimators that can be used in a stochastic optimization scheme using only samples from the behavior policy. Our method finds an $\varepsilon$-optimal policy with $O(\varepsilon^{-4})$ samples, improving on the previous $O(\varepsilon^{-5})$, while being computationally efficient for infinite-horizon discounted and average-reward MDPs with realizable linear function approximation and partial coverage. Moreover, to the best of our knowledge, this is the first theoretical result for average-reward offline RL.

10 May 2024 in arXiv
Verified
Preprint
Open access
PDF file
DMDavide Maran
Davide Maran
AMAlberto Maria Metelli
Alberto Maria Metelli
MPMatteo Papini
Matteo Papini
MRMarcello Restelli
Marcello Restelli
We consider the problem of learning an $\varepsilon$-optimal policy in a general class of continuous-space Markov decision processes (MDPs) having smooth Bellman operators. Given access to a generative model, we achieve rate-optimal sample complexity by performing a simple, \emph{perturbed} version of least-squares value iteration with orthogonal trigonometric polynomials as features. Key to our solution is a novel projection technique based on ideas from harmonic analysis. Our~$\widetilde{\mathcal{O}}(ε^{-2-d/(ν+1)})$ sample complexity, where $d$ is the dimension of the state-action space and $ν$ the order of smoothness, recovers the state-of-the-art result of discretization approaches for the special case of Lipschitz MDPs $(ν=0)$. At the same time, for $ν\to\infty$, it recovers and greatly generalizes the $\mathcal{O}(ε^{-2})$ rate of low-rank MDPs, which are more amenable to regression approaches. In this sense, our result bridges the gap between two popular but conflicting perspectives on continuous-space MDPs.