logo-polimi
Loading...
Manifesto
Struttura Corso di Studi
Cerca/Visualizza Manifesto
Regolamento didattico
Indicatori corsi di studio
Internazionalizzazione
Orario Personalizzato
Il tuo orario personalizzato è disabilitato
Abilita
Ricerche
Cerca Docenti
Attività docente
Cerca Insegnamenti
Cerca insegnamenti degli Ordinamenti precedenti al D.M.509
Erogati in lingua Inglese
Le informazioni sulla didattica, sulla ricerca e sui compiti istituzionali riportate in questa pagina sono certificate dall'Ateneo; ulteriori informazioni, redatte a cura del docente, sono disponibili sulla pagina web personale e nel curriculum vitae indicati nella scheda.
English
Informazioni
DocenteRestelli Marcello
QualificaProfessore ordinario a tempo pieno
Dipartimento d'afferenzaDipartimento di Elettronica, Informazione e Bioingegneria
Settore Scientifico DisciplinareIINF-05/A - Sistemi Di Elaborazione Delle Informazioni
Curriculum VitaeScarica il CV (540.12Kb - 11/03/2024)
OrcIDhttps://orcid.org/0000-0002-6322-1076

Contatti
Orario di ricevimento
DipartimentoPianoUfficioGiornoOrarioTelefonoFaxNote
DEI------MercoledìDalle 11:00
Alle 13:00		4015---Si consiglia di prendere appuntamento via email con il docente
E-mailmarcello.restelli@polimi.it
Pagina web redatta a cura del docentehttp://home.deib.polimi.it/restelli/

Fonte dati: RE.PUBLIC@POLIMI - Research Publications at Politecnico di Milano

Elenco delle pubblicazioni e dei prodotti della ricerca per l'anno 2026
Nessun prodotto attualmente registrato nell'anno 2026


Elenco delle pubblicazioni e dei prodotti della ricerca per l'anno 2025 (Mostra tutto | Nascondi tutto)
Tipologia Titolo Pubblicazione/Prodotto
Poster
Power Grid Control with Graph-Based Distributed Reinforcement Learning (Mostra >>)
Reinforcement Learning vs Optimal Control: Sparse Nonlinear Dynamical Systems Between Theory and Practice (Mostra >>)
Contributo in Atti di convegno
A reinforcement learning approach for optimal control in microgrids (Mostra >>)
Achieving \mathcal{O}(\sqrt{T}) Regret in Average-Reward POMDPs with Known Observation Models (Mostra >>)
Enhancing Diversity in Parallel Agents: A Maximum State Entropy Exploration Story (Mostra >>)
Limitations of Physics-Informed Neural Networks: a Study on Smart Grid Surrogation (Mostra >>)
“So, Tell Me About Your Policy…”: Distillation of Interpretable Policies from Deep Reinforcement Learning Agents (Mostra >>)
Articoli su riviste
A novel digital twin for battery energy storage systems in micro-grids (Mostra >>)
Factored-Reward Bandits with Intermediate Observations: Regret Minimization and Best Arm Identification (Mostra >>)
Search or split: policy gradient with adaptive policy space (Mostra >>)


Elenco delle pubblicazioni e dei prodotti della ricerca per l'anno 2024 (Mostra tutto | Nascondi tutto)
Tipologia Titolo Pubblicazione/Prodotto
Poster
Policy Gradient Methods with Adaptive Policy Spaces (Mostra >>)
State and Action Factorization in Power Grids (Mostra >>)
Contributo in Atti di convegno
A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics (Mostra >>)
Autoregressive Bandits (Mostra >>)
Bandits with Ranking Feedback (Mostra >>)
Best Arm Identification for Stochastic Rising Bandits (Mostra >>)
Building Surrogate Models Using Trajectories of Agents Trained by Reinforcement Learning (Mostra >>)
Causal feature selection via transfer entropy (Mostra >>)
EXPLOITING CAUSAL GRAPH PRIORS WITH POSTERIOR SAMPLING FOR REINFORCEMENT LEARNING (Mostra >>)
Factored-Reward Bandits with Intermediate Observations (Mostra >>)
Graph-Triggered Rising Bandits (Mostra >>)
How to explore with belief: state entropy maximization in POMDPs (Mostra >>)
Interpretable Machine Learning for Extreme Events detection: An application to droughts in the Po River Basin (Mostra >>)
Interpretable Target-Feature Aggregation for Multi-task Learning Based on Bias-Variance Analysis (Mostra >>)
Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs (Mostra >>)
No-Regret Reinforcement Learning in Smooth MDPs (Mostra >>)
Online markov decision processes configuration with continuous decision space (Mostra >>)
Optimal multi-fidelity best-arm identification (Mostra >>)
Parameterized Projected Bellman Operator (Mostra >>)
Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs (Mostra >>)
Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning (Mostra >>)
The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough (Mostra >>)
The Power of Hybrid Learning in Industrial Robotics: Efficient Grasping Strategies with Supervised-Driven Reinforcement Learning (Mostra >>)
Transfer Learning for Dynamical Systems Models via Autoencoders and GANs (Mostra >>)
Articoli su riviste
A Provably Efficient Option-Based Algorithm for both High-Level and Low-Level Learning (Mostra >>)
A Reinforcement Learning controller optimizing costs and battery State of Health in smart grids (Mostra >>)
Interpretable linear dimensionality reduction based on bias-variance analysis (Mostra >>)
Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds (Mostra >>)
Switching Latent Bandits (Mostra >>)


Elenco delle pubblicazioni e dei prodotti della ricerca per l'anno 2023 (Mostra tutto | Nascondi tutto)
Tipologia Titolo Pubblicazione/Prodotto
Abstract in Atti di convegno
A Brief Guide to Multi-Objective Reinforcement Learning and Planning JAAMAS track (Mostra >>)
Contributo in Atti di convegno
A Provably Efficient Option-Based Algorithm for both High-Level and Low-Level Learning (Mostra >>)
A Tale of Sampling and Estimation in Discounted Reinforcement Learning (Mostra >>)
Distributional Policy Evaluation: a Maximum Entropy approach to Representation Learning (Mostra >>)
Dynamic Pricing with Volume Discounts in Online Settings (Mostra >>)
Dynamical Linear Bandits (Mostra >>)
Information-Theoretic Regret Bounds for Bandits with Fixed Expert Advice (Mostra >>)
On the Relation between Policy Improvement and Off-Policy Minimum-Variance Policy Evaluation (Mostra >>)
Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization (Mostra >>)
Simultaneously Updating All Persistence Values in Reinforcement Learning (Mostra >>)
Stepsize Learning for Policy Gradient Methods in Contextual Markov Decision Processes (Mostra >>)
Switching Latent Bandits (Mostra >>)
Tight Performance Guarantees of Imitator Policies with Continuous Actions (Mostra >>)
Towards Theoretical Understanding of Inverse Reinforcement Learning (Mostra >>)
Towards an AI-Based Framework for Autonomous Design and Construction: Learning from Reinforcement Learning Success in RTS Games (Mostra >>)
Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach (Mostra >>)
Truncating Trajectories in Monte Carlo Reinforcement Learning (Mostra >>)
Wasserstein Actor-Critic: Directed Exploration via Optimism for Continuous-Actions Control (Mostra >>)
Articoli su riviste
ARLO: A framework for Automated Reinforcement Learning (Mostra >>)
An Option-Dependent Analysis of Regret Minimization Algorithms in Finite-Horizon Semi-MDP (Mostra >>)
Convex Reinforcement Learning in Finite Trials (Mostra >>)
Dealer markets: A reinforcement learning mean field game approach (Mostra >>)
IWDA: Importance Weighting for Drift Adaptation in Streaming Supervised Learning Problems (Mostra >>)
Optimizing Empty Container Repositioning and Fleet Deployment via Configurable Semi-POMDPs (Mostra >>)
Risk-averse optimization of reward-based coherent risk measures (Mostra >>)
The EU-funded I3LUNG Project: Integrative Science, Intelligent Data Platform for Individualized LUNG Cancer Care With Immunotherapy (Mostra >>)


Elenco delle pubblicazioni e dei prodotti della ricerca per l'anno 2022 (Mostra tutto | Nascondi tutto)
Tipologia Titolo Pubblicazione/Prodotto
Abstract in Atti di convegno
Advancing drought monitoring via feature extraction and multi-task learning algorithms (Mostra >>)
Brevetti
A COMPUTER IMPLEMENTED METHOD FOR REAL TIME QUANTUM COMPILING BASED ON ARTIFICIAL INTELLIGENCE (Mostra >>)
Contributi su volumi (Capitolo o Saggio)
AI, Machine Learning e Data Mining (Mostra >>)
Contributo in Atti di convegno
Addressing Non-Stationarity in FX Trading with Online Model Selection of Offline RL Experts (Mostra >>)
Balancing Sample Efficiency and Suboptimality in Inverse Reinforcement Learning (Mostra >>)
Challenging Common Assumptions in Convex Reinforcement Learning (Mostra >>)
Dark-Pool Smart Order Routing: a Combinatorial Multi-armed Bandit Approach (Mostra >>)
Delayed Reinforcement Learning by Imitation (Mostra >>)
Finite Sample Analysis of Mean-Volatility Actor-Critic for Risk-Averse Reinforcement Learning (Mostra >>)
Goal-Directed Planning via Hindsight Experience Replay (Mostra >>)
Learning in Markov Games: can we exploit a general-sum opponent? (Mostra >>)
Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization (Mostra >>)
Multi-Armed Bandit Problem with Temporally-Partitioned Rewards: When Partial Feedback Counts (Mostra >>)
Multi-Fidelity Best-Arm Identification (Mostra >>)
Off-Policy Evaluation with Deficient Support Using Side Information (Mostra >>)
Pricing the Long Tail by Explainable Product Aggregation and Monotonic Bandits (Mostra >>)
Reward-Free Policy Space Compression for Reinforcement Learning (Mostra >>)
Stochastic Rising Bandits (Mostra >>)
Storehouse: a Reinforcement Learning Environment for Optimizing Warehouse Management (Mostra >>)
The Importance of Non-Markovianity in Maximum State Entropy Exploration (Mostra >>)
Trust Region Meta Learning for Policy Optimization (Mostra >>)
Unsupervised Reinforcement Learning in Multiple Environments (Mostra >>)
Articoli su riviste
A practical guide to multi-objective reinforcement learning and planning (Mostra >>)
An online state of health estimation method for lithium-ion batteries based on time partitioning and data-driven model identification (Mostra >>)
Machine Learning Using Real-World and Translational Data to Improve Treatment Selection for NSCLC Patients Treated with Immunotherapy (Mostra >>)
Online joint bid/daily budget optimization of Internet advertising campaigns (Mostra >>)
Policy space identification in configurable environments (Mostra >>)
Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients (Mostra >>)
Risk-averse policy optimization via risk-neutral policy optimization (Mostra >>)
Smoothing policies and safe policy gradients (Mostra >>)
manifesti v. 3.13.1 / 3.13.1
Area Servizi ICT
17/02/2026