METELLI, ALBERTO MARIA

METELLI, ALBERTO MARIA  

DIPARTIMENTO DI ELETTRONICA, INFORMAZIONE E BIOINGEGNERIA  

Mostra records
Risultati 1 - 14 di 14 (tempo di esecuzione: 0.028 secondi).
Titolo Data di pubblicazione Autori File
A Provably Efficient Option-Based Algorithm for both High-Level and Low-Level Learning 1-gen-2024 G. DrappoA. M. MetelliM. Restelli
A unified view of configurable Markov Decision Processes: Solution concepts, value functions, and operators 1-gen-2022 Metelli A. M.
An Option-Dependent Analysis of Regret Minimization Algorithms in Finite-Horizon Semi-MDP 1-gen-2023 Gianluca DrappoAlberto Maria MetelliMarcello Restelli
ARLO: A framework for Automated Reinforcement Learning 1-gen-2023 Mussi, MarcoMetelli, Alberto MariaTrovo, FrancescoRestelli, Marcello +
Combining reinforcement learning with rule-based controllers for transparent and general decision-making in autonomous driving 1-gen-2020 Likmeta AmarildoMetelli Alberto MariaTirinzoni AndreaGiol RiccardoRestelli Marcello +
Dealing with multiple experts and non-stationarity in inverse reinforcement learning: an application to real-life problems 1-gen-2021 Likmeta A.Metelli A. M.Ramponi G.Tirinzoni A.Giuliani M.Restelli M.
Importance Sampling Techniques for Policy Optimization 1-gen-2020 Metelli Alberto MariaPapini MatteoMontali NicoRestelli Marcello
Interpretable linear dimensionality reduction based on bias-variance analysis 1-gen-2024 Bonetti P.Metelli A. M.Restelli M.
IWDA: Importance Weighting for Drift Adaptation in Streaming Supervised Learning Problems 1-gen-2023 Fedeli FilippoMetelli Alberto MariaTrovo' FrancescoRestelli Marcello
On the use of the policy gradient and Hessian in inverse reinforcement learning 1-gen-2020 Metelli A. M.Pirotta M.Restelli M.
Optimizing Empty Container Repositioning and Fleet Deployment via Configurable Semi-POMDPs 1-gen-2023 Riccardo PoianiAlberto Maria MetelliMarcello Restelli +
Policy space identification in configurable environments 1-gen-2022 Metelli A. M.Restelli M. +
Safe policy iteration: A monotonically improving approximate policy iteration approach 1-gen-2021 Metelli A. M.Pirotta M.Calandriello D.Restelli M.
Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds 1-gen-2024 Papini, MatteoMetelli, Alberto MariaRestelli, Marcello +