Follow
Marco Mussi
Marco Mussi
Postdoctoral Researcher, Politecnico di Milano
Verified email at polimi.it - Homepage
Title
Cited by
Cited by
Year
A voltage dynamic-based state of charge estimation method for batteries storage systems
M Mussi, L Pellegrino, M Restelli, F Trovò
Journal of Energy Storage 44, 103309, 2021
182021
Pricing the Long Tail by Explainable Product Aggregation and Monotonic Bandits
M Mussi, G Genalti, F Trovò, A Nuara, N Gatti, M Restelli
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and …, 2022
122022
An online state of health estimation method for lithium-ion batteries based on time partitioning and data-driven model identification
M Mussi, L Pellegrino, M Restelli, F Trovò
Journal of Energy Storage 55, 105467, 2022
112022
Dynamical Linear Bandits
M Mussi, AM Metelli, M Restelli
International Conference on Machine Learning, 25563-25587, 2023
52023
Dynamic pricing with volume discounts in online settings
M Mussi, G Genalti, A Nuara, F Trovó, M Restelli, N Gatti
Proceedings of the AAAI Conference on Artificial Intelligence 37 (13), 15560 …, 2023
52023
ARLO: A framework for Automated Reinforcement Learning
M Mussi, D Lombarda, AM Metelli, F Trovò, M Restelli
Expert Systems with Applications, 119883, 2023
52023
Best Arm Identification for Stochastic Rising Bandits
M Mussi, A Montenegro, F Trovó, M Restelli, AM Metelli
arXiv preprint arXiv:2302.07510, 2023
42023
Autoregressive bandits
F Bacchiocchi, G Genalti, D Maran, M Mussi, M Restelli, N Gatti, ...
International Conference on Artificial Intelligence and Statistics, 937-945, 2024
32024
A Reinforcement Learning controller optimizing costs and battery State of Health in smart grids
M Mussi, L Pellegrino, OF Pindaro, M Restelli, F Trovò
Journal of Energy Storage 82, 110572, 2024
32024
Graph-Triggered Rising Bandits
G Genalti, M Mussi, N Gatti, M Restelli, M Castiglioni, AM Metelli
Forty-first International Conference on Machine Learning, 2024
22024
Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning
A Montenegro, M Mussi, M Papini, AM Metelli
arXiv preprint arXiv:2407.10775, 2024
12024
Learning Optimal Deterministic Policies with Stochastic Policy Gradients
A Montenegro, M Mussi, AM Metelli, M Papini
arXiv preprint arXiv:2405.02235, 2024
12024
Dynamic Pricing with Online Data Aggregation and Learning
G Genalti, M Mussi, A Nuara, N Gatti
European Workshop on Reinforcement Learning, 2022
12022
Bridging Rested and Restless Bandits with Graph-Triggering: Rising and Rotting
G Genalti, M Mussi, N Gatti, M Restelli, M Castiglioni, AM Metelli
arXiv preprint arXiv:2409.05980, 2024
2024
State and Action Factorization in Power Grids
G Losapio, D Beretta, M Mussi, AM Metelli, M Restelli
arXiv preprint arXiv:2409.04467, 2024
2024
Open Problem: Tight Bounds for Kernelized Multi-Armed Bandits with Bernoulli Rewards
M Mussi, S Drago, AM Metelli
arXiv preprint arXiv:2407.06321, 2024
2024
Open Problem: Tight Bounds for Bernoulli Rewards in Kernelized Multi-Armed Bandits
S Drago, M Mussi
2024
Online Learning Methods for Pricing and Advertising
M Mussi
2023
A Best Arm Identification Approach for Stochastic Rising Bandits
A Montenegro, M Mussi, F Trovo, M Restelli, AM Metelli
Workshop on New Frontiers in Learning, Control, and Dynamical Systems at …, 2023
2023
Dynamical Linear Bandits for Long-Lasting Vanishing Rewards
M Mussi, AM Metelli, M Restelli
Complex Feedback in Online Learning Workshop at International Conference of …, 2022
2022
The system can't perform the operation now. Try again later.
Articles 1–20