Marcello Restelli

Venues

Frequent coauthors

Papers

1. Online Market Making and the Value of Observing the Order Book
   COLT 2026 ·

   Davide Maran

   DBLP profile ↗ORCID search ↗
2. "So, Tell Me About Your Policy...": Distillation of Interpretable Policies from Deep Reinforcement Learning Agents
   ECAI 2025 ·

   Giovanni Dispoto

   DBLP profile ↗ORCID search ↗
3. Achieving $\widetilde{\mathcal{O}}(\sqrt{T})$ Regret in Average-Reward POMDPs with Known Observation Models
   AISTATS 2025 ·

   Alessio Russo

   DBLP profile ↗ORCID search ↗
4. Efficient Exploitation of Hierarchical Structure in Sparse Reward Reinforcement Learning
   AISTATS 2025 ·

   Gianluca Drappo

   DBLP profile ↗ORCID search ↗
5. Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story
   ICML 2025 ·

   Vincenzo De Paola

   DBLP profile ↗ORCID search ↗
6. Spectral Learning for Infinite-Horizon Average-Reward POMDPs
   NeurIPS 2025 ·

   Alessio Russo

   DBLP profile ↗ORCID search ↗
7. Towards Principled Unsupervised Multi-Agent Reinforcement Learning
   NeurIPS 2025 ·

   Riccardo Zamboni

   DBLP profile ↗ORCID search ↗
8. A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics
   NeurIPS 2024 ·

   Puze Liu

   DBLP profile ↗ORCID search ↗
9. Autoregressive Bandits
   AISTATS 2024 ·

   Francesco Bacchiocchi

   DBLP profile ↗ORCID search ↗
10. Bandits with Ranking Feedback
    NeurIPS 2024 ·

    Davide Maran

    DBLP profile ↗ORCID search ↗
11. Best Arm Identification for Stochastic Rising Bandits
    ICML 2024 ·

    Marco Mussi

    DBLP profile ↗ORCID search ↗
12. Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning
    ICLR 2024 ·

    Mirco Mutti

    DBLP profile ↗ORCID search ↗
13. Factored-Reward Bandits with Intermediate Observations
    ICML 2024 ·

    Marco Mussi

    DBLP profile ↗ORCID search ↗
14. Graph-Triggered Rising Bandits
    ICML 2024 ·

    Gianmarco Genalti

    DBLP profile ↗ORCID search ↗
15. How to Explore with Belief: State Entropy Maximization in POMDPs
    ICML 2024 ·

    Riccardo Zamboni

    DBLP profile ↗ORCID search ↗
16. Interpetable Target-Feature Aggregation for Multi-task Learning Based on Bias-Variance Analysis
    ECML-PKDD 2024 ·

    Paolo Bonetti

    DBLP profile ↗ORCID search ↗
17. Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs
    NeurIPS 2024 ·

    Davide Maran

    DBLP profile ↗ORCID search ↗
18. No-Regret Reinforcement Learning in Smooth MDPs
    ICML 2024 ·

    Davide Maran

    DBLP profile ↗ORCID search ↗
19. Online Markov Decision Processes Configuration with Continuous Decision Space
    AAAI 2024 ·

    Davide Maran

    DBLP profile ↗ORCID search ↗
20. Optimal Multi-Fidelity Best-Arm Identification
    NeurIPS 2024 ·

    Riccardo Poiani

    DBLP profile ↗ORCID search ↗
21. Parameterized Projected Bellman Operator
    AAAI 2024 ·

    Théo Vincent

    DBLP profile ↗ORCID search ↗
22. Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs
    COLT 2024 ·

    Davide Maran

    DBLP profile ↗ORCID search ↗
23. Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning
    NeurIPS 2024 ·

    Riccardo Poiani

    DBLP profile ↗ORCID search ↗