| Stochastic variance-reduced policy gradient M Papini, D Binaghi, G Canonaco, M Pirotta, M Restelli Proceedings of the 35th International Conference on Machine Learning 80 …, 2018 | 216 | 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 | 123 | 2019 |
| Policy optimization via importance sampling AM Metelli, M Papini, F Faccio, M Restelli Advances in Neural Information Processing Systems 31, 2018 | 114 | 2018 |
| Risk-averse trust region optimization for reward-volatility reduction L Bisi, L Sabbioni, E Vittori, M Papini, M Restelli arXiv preprint arXiv:1912.03193, 2019 | 74 | 2019 |
| Importance sampling techniques for policy optimization AM Metelli, M Papini, N Montali, M Restelli Journal of Machine Learning Research 21 (141), 1-75, 2020 | 59 | 2020 |
| Gradient-aware model-based policy search P D'Oro, AM Metelli, A Tirinzoni, M Papini, M Restelli Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 3801-3808, 2020 | 48 | 2020 |
| Adaptive batch size for safe policy gradients M Papini, M Pirotta, M Restelli Advances in neural information processing systems 30, 2017 | 48 | 2017 |
| Smoothing policies and safe policy gradients M Papini, M Pirotta, M Restelli Machine Learning 111 (11), 4081-4137, 2022 | 45 | 2022 |
| Optimistic policy optimization via multiple importance sampling M Papini, AM Metelli, L Lupo, M Restelli International Conference on Machine Learning, 4989-4999, 2019 | 41 | 2019 |
| Leveraging good representations in linear contextual bandits M Papini, A Tirinzoni, M Restelli, A Lazaric, M Pirotta International Conference on Machine Learning, 8371-8380, 2021 | 34 | 2021 |
| Reinforcement learning in linear mdps: Constant regret and representation selection M Papini, A Tirinzoni, A Pacchiano, M Restelli, A Lazaric, M Pirotta Advances in Neural Information Processing Systems 34, 16371-16383, 2021 | 23 | 2021 |
| Lifting the information ratio: An information-theoretic analysis of thompson sampling for contextual bandits G Neu, I Olkhovskaia, M Papini, L Schwartz Advances in Neural Information Processing Systems 35, 9486-9498, 2022 | 21 | 2022 |
| Balancing learning speed and stability in policy gradient via adaptive exploration M Papini, A Battistello, M Restelli International conference on artificial intelligence and statistics, 1188-1199, 2020 | 19 | 2020 |
| 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 | 15 | 2021 |
| Importance-weighted offline learning done right G Gabbianelli, G Neu, M Papini International Conference on Algorithmic Learning Theory, 614-634, 2024 | 10 | 2024 |
| Offline primal-dual reinforcement learning for linear mdps G Gabbianelli, G Neu, M Papini, NM Okolo International Conference on Artificial Intelligence and Statistics, 3169-3177, 2024 | 9 | 2024 |
| Online adversarial mdps with off-policy feedback and known transitions F Bacchiocchi, FE Stradi, M Papini, AM Metelli, N Gatti Sixteenth European Workshop on Reinforcement Learning, 2023 | 9 | 2023 |
| No-regret reinforcement learning in smooth mdps D Maran, AM Metelli, M Papini, M Restell arXiv preprint arXiv:2402.03792, 2024 | 7 | 2024 |
| Scalable representation learning in linear contextual bandits with constant regret guarantees A Tirinzoni, M Papini, A Touati, A Lazaric, M Pirotta Advances in Neural Information Processing Systems 35, 2307-2319, 2022 | 7 | 2022 |
| Projection by convolution: Optimal sample complexity for reinforcement learning in continuous-space mdps D Maran, AM Metelli, M Papini, M Restelli The Thirty Seventh Annual Conference on Learning Theory, 3743-3774, 2024 | 5 | 2024 |
Marcello RestelliAssociate Professor, Politecnico di MilanoVerified email at polimi.it
