Matteo Papini

25 papers · 2017–2026 · 8 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (9) 🗺️ Taxonomy Completionist (25) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (6) 🌍 Conference Polyglot (8) 🏃 Academic Marathon (8) 🤝 Dynamic Duo (14) 🔬 Deep Specialist (12) 💎 Century Club (24) 🗃️ Keyword Collector (87) ⚡ Prolific Year (9) 🔥 Unstoppable (9)

Conferences

NIPS (7) ICML (6) AAAI (3) AISTATS (2) ALT (2) COLT (2) IJCAI (2) JMLR (1)

Top co-authors

Marcello Restelli (14) Alberto Maria Metelli (12) Matteo Pirotta (5) Gergely Neu (5) Andrea Tirinzoni (4) Davide Maran (3) Alessandro Montenegro (3) Alessandro Lazaric (3) Germano Gabbianelli (3) Marco Mussi (3)

Keywords

reinforcement learning (7) policy gradient (6) regret bound (5) contextual bandit (4) online learning (4) policy optimization (4) importance sampling (4) continuous control (4) markov decision process (4) function approximation (4) representation learning (3) linear mdp (2) sample complexity (2) online algorithm (2) constant regret (2) policy search (2) off-policy learning (2) regret minimization (2) variance reduction (2) pessimistic estimator (2)

Papers

Do It for HER: First-Order Temporal Logic Reward Specification in Reinforcement Learning AAAI 2026

Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity ICML 2025

Importance-Weighted Offline Learning Done Right ALT 2024

Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs NIPS 2024

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

Offline Primal-Dual Reinforcement Learning for Linear MDPs AISTATS 2024

Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs COLT 2024

Optimistic Information Directed Sampling COLT 2024

No-Regret Reinforcement Learning in Smooth MDPs ICML 2024

Learning Optimal Deterministic Policies with Stochastic Policy Gradients ICML 2024

Online Learning with Off-Policy Feedback in Adversarial MDPs IJCAI 2024

Online Learning with Off-Policy Feedback ALT 2023

Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits NIPS 2022

Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees NIPS 2022

Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection NIPS 2021

Leveraging Good Representations in Linear Contextual Bandits ICML 2021

Policy Optimization as Online Learning with Mediator Feedback AAAI 2021

Importance Sampling Techniques for Policy Optimization JMLR 2020

Balancing Learning Speed and Stability in Policy Gradient via Adaptive Exploration AISTATS 2020

Gradient-Aware Model-Based Policy Search AAAI 2020

Risk-Averse Trust Region Optimization for Reward-Volatility Reduction IJCAI 2020

Optimistic Policy Optimization via Multiple Importance Sampling ICML 2019

Stochastic Variance-Reduced Policy Gradient ICML 2018

Policy Optimization via Importance Sampling NIPS 2018

Adaptive Batch Size for Safe Policy Gradients NIPS 2017