| Sequential transfer in reinforcement learning with a generative model A Tirinzoni, R Poiani, M Restelli International Conference on Machine Learning, 9481-9492, 2020 | 32 | 2020 |
| Multi-fidelity best-arm identification R Poiani, AM Metelli, M Restelli Advances in Neural Information Processing Systems 35, 17857-17870, 2022 | 14 | 2022 |
| Meta-Reinforcement Learning by Tracking Task Non-stationarity R Poiani, A Tirinzoni, M Restelli Proceedings of the Thirtieth International Joint Conference on Artificial …, 2021 | 13 | 2021 |
| Truncating Trajectories in Monte Carlo Reinforcement Learning R Poiani, AM Metelli, M Restelli International Conference on Machine Learning, 2023 | 11 | 2023 |
| Optimal multi-fidelity best-arm identification R Poiani, R Degenne, E Kaufmann, AM Metelli, M Restelli Advances in Neural Information Processing Systems 37, 121882-121927, 2024 | 10 | 2024 |
| Sub-optimal experts mitigate ambiguity in inverse reinforcement learning R Poiani, C Gabriele, AM Metelli, M Restelli Advances in Neural Information Processing Systems 37, 85778-85823, 2024 | 9* | 2024 |
| Best-arm identification in unimodal bandits R Poiani, M Jourdan, E Kaufmann, R Degenne AISTATS 2025, 2024 | 8 | 2024 |
| Truncating trajectories in Monte Carlo policy evaluation: An adaptive approach R Poiani, N Nobili, AM Metelli, M Restelli Advances in Neural Information Processing Systems 36, 2024 | 6 | 2024 |
| Optimizing Empty Container Repositioning and Fleet Deployment via Configurable Semi-POMDPs R Poiani, C Stirbu, AM Metelli, M Restelli IEEE Transactions on Intelligent Transportation Systems 25 (5), 4704-4711, 2023 | 4 | 2023 |
| Pure Exploration under Mediators' Feedback R Poiani, AM Metelli, M Restelli NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in …, 2023 | 4 | 2023 |
| Non-Asymptotic Analysis of (Sticky) Track-and-Stop R Poiani, M Bernasconi, A Celli arXiv preprint arXiv:2505.22475, 2025 | | 2025 |
| Pure Exploration with Infinite Answers R Poiani, M Bernasconi, A Celli arXiv preprint arXiv:2505.22473, 2025 | | 2025 |
| Novel perspectives on multi-fidelity sequential decision-making R Poiani | | 2024 |
Marcello RestelliFull Professor, Politecnico di MilanoVerified email at polimi.it
