Marco Mussi

12 papers · 2023–2025 · 4 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (9) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (10) 🧭 Keyword Pioneer 🌍 Conference Polyglot (4) 🤝 Dynamic Duo (11) ⚡ Prolific Year (6) 💎 Century Club (12)

Conferences

ICML (9) AAAI (1) AISTATS (1) NIPS (1)

Top co-authors

Alberto Maria Metelli (11) Marcello Restelli (6) Simone Drago (4) Alessandro Montenegro (4) Matteo Papini (3) Nicola Gatti (3) Gianmarco Genalti (3) Francesco Trovò (2) Alessandro Nuara (1) Davide Maran (1)

Keywords

regret minimization (2) sequential decision-making (2) online learning (2) constrained optimization (1) continuous control (1) sequential decision (1) primal-dual algorithm (1) online learning algorithm (1) multi-armed bandit (1) regret bound (1) online algorithm (1) hidden state (1) optimistic algorithm (1) linear bandit (1) dynamic pricing (1) risk measure (1) autoregressive process (1) optimization horizon (1) a/b testing (1) linear dynamics (1)

Papers

Position: Constants are Critical in Regret Bounds for Reinforcement Learning ICML 2025

Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity ICML 2025

Sleeping Reinforcement Learning ICML 2025

Towards Theoretical Understanding of Sequential Decision Making with Preference Feedback ICML 2025

Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning NIPS 2024

Best Arm Identification for Stochastic Rising Bandits ICML 2024

Factored-Reward Bandits with Intermediate Observations ICML 2024

Autoregressive Bandits AISTATS 2024

Graph-Triggered Rising Bandits ICML 2024

Learning Optimal Deterministic Policies with Stochastic Policy Gradients ICML 2024

Dynamical Linear Bandits ICML 2023

Dynamic Pricing with Volume Discounts in Online Settings AAAI 2023