| Policy Optimization via Importance Sampling AM Metelli, M Papini, F Faccio, M Restelli Advances in Neural Information Processing Systems 31, 5442-5454, 2018 | 94 | 2018 |
| Feature selection via mutual information: New theoretical insights M Beraha, AM Metelli, M Papini, A Tirinzoni, M Restelli 2019 international joint conference on neural networks (IJCNN), 1-9, 2019 | 65 | 2019 |
| Combining reinforcement learning with rule-based controllers for transparent and general decision-making in autonomous driving A Likmeta, AM Metelli, A Tirinzoni, R Giol, M Restelli, D Romano Robotics and Autonomous Systems 131, 103568, 2020 | 51 | 2020 |
| Importance sampling techniques for policy optimization AM Metelli, M Papini, N Montali, M Restelli The Journal of Machine Learning Research 21 (1), 5552-5626, 2020 | 39 | 2020 |
| Configurable Markov Decision Processes AM Metelli, M Mutti, M Restelli Proceedings of the 35th International Conference on Machine Learning 80 …, 2018 | 39 | 2018 |
| Compatible reward inverse reinforcement learning AM Metelli, M Pirotta, M Restelli The Thirty-first Annual Conference on Neural Information Processing Systems …, 2017 | 39 | 2017 |
| Gradient-aware model-based policy search P D'Oro, AM Metelli, A Tirinzoni, M Papini, M Restelli The Thirty-Fourth AAAI Conference on Artificial Intelligence, 3801-3808, 2020 | 33 | 2020 |
| Optimistic policy optimization via multiple importance sampling M Papini, AM Metelli, L Lupo, M Restelli International Conference on Machine Learning, 4989-4999, 2019 | 32 | 2019 |
| Truly batch model-free inverse reinforcement learning about multiple intentions G Ramponi, A Likmeta, AM Metelli, A Tirinzoni, M Restelli International conference on artificial intelligence and statistics, 2359-2369, 2020 | 29 | 2020 |
| Control Frequency Adaptation via Action Persistence in Batch Reinforcement Learning AM Metelli, F Mazzolini, L Bisi, L Sabbioni, M Restelli International Conference on Machine Learning 119, 6862--6873, 2020 | 29 | 2020 |
| Propagating uncertainty in reinforcement learning via wasserstein barycenters AM Metelli, A Likmeta, M Restelli Advances in Neural Information Processing Systems 32, 2019 | 26 | 2019 |
| Content-based approaches for cold-start job recommendations M Bianchi, F Cesaro, F Ciceri, M Dagrada, A Gasparin, D Grattarola, ... Proceedings of the Recommender Systems Challenge 2017, 1-5, 2017 | 21 | 2017 |
| Subgaussian and differentiable importance sampling for off-policy evaluation and learning AM Metelli, A Russo, M Restelli Advances in neural information processing systems 34, 8119-8132, 2021 | 19 | 2021 |
| Dealing with multiple experts and non-stationarity in inverse reinforcement learning: an application to real-life problems A Likmeta, AM Metelli, G Ramponi, A Tirinzoni, M Giuliani, M Restelli Machine Learning 110, 2541-2576, 2021 | 18 | 2021 |
| Reinforcement learning in configurable continuous environments AM Metelli, E Ghelfi, M Restelli International Conference on Machine Learning, 4546-4555, 2019 | 14 | 2019 |
| Policy space identification in configurable environments AM Metelli, G Manneschi, M Restelli Machine Learning, 1-53, 2021 | 12 | 2021 |
| Provably efficient learning of transferable rewards AM Metelli, G Ramponi, A Concetti, M Restelli International Conference on Machine Learning, 7665-7676, 2021 | 11 | 2021 |
| Policy Optimization as Online Learning with Mediator Feedback AM Metelli, M Papini, P D'Oro, M Restelli Proceedings of the AAAI Conference on Artificial Intelligence 35 (10), 8958-8966, 2021 | 9 | 2021 |
| Stochastic rising bandits AM Metelli, F Trovo, M Pirola, M Restelli International Conference on Machine Learning, 15421-15457, 2022 | 8 | 2022 |
| Lifelong hyper-policy optimization with multiple importance sampling regularization P Liotet, F Vidaich, AM Metelli, M Restelli Proceedings of the AAAI Conference on Artificial Intelligence 36 (7), 7525-7533, 2022 | 8 | 2022 |
Marcello RestelliAssociate Professor, Politecnico di MilanoVerified email at polimi.it
