Matteo Pirotta
Matteo Pirotta
Research Scientist, Facebook AI Research
E-mail confirmado em fb.com - Página inicial
Título
Citado por
Citado por
Ano
Stochastic variance-reduced policy gradient
M Papini, D Binaghi, G Canonaco, M Pirotta, M Restelli
International conference on machine learning, 4026-4035, 2018
792018
Safe policy iteration
M Pirotta, M Restelli, A Pecorino, D Calandriello
International Conference on Machine Learning, 307-315, 2013
762013
Efficient bias-span-constrained exploration-exploitation in reinforcement learning
R Fruit, M Pirotta, A Lazaric, R Ortner
International Conference on Machine Learning, 1578-1586, 2018
632018
Adaptive step-size for policy gradient methods
M Pirotta, M Restelli, L Bascetta
Advances in Neural Information Processing Systems 26, 1394-1402, 2013
632013
Policy gradient in lipschitz markov decision processes
M Pirotta, M Restelli, L Bascetta
Machine Learning 100 (2), 255-283, 2015
562015
Frequentist regret bounds for randomized least-squares value iteration
A Zanette, D Brandfonbrener, E Brunskill, M Pirotta, A Lazaric
International Conference on Artificial Intelligence and Statistics, 1954-1964, 2020
492020
Multi-objective reinforcement learning with continuous pareto frontier approximation
M Pirotta, S Parisi, M Restelli
Twenty-ninth AAAI conference on artificial intelligence, 2015
482015
Policy gradient approaches for multi-objective sequential decision making
S Parisi, M Pirotta, N Smacchia, L Bascetta, M Restelli
2014 International Joint Conference on Neural Networks (IJCNN), 2323-2330, 2014
402014
Exploration-exploitation in constrained mdps
Y Efroni, S Mannor, M Pirotta
arXiv preprint arXiv:2003.02189, 2020
382020
Inverse reinforcement learning through policy gradient minimization
M Pirotta, M Restelli
Thirtieth AAAI Conference on Artificial Intelligence, 2016
312016
Boosted fitted q-iteration
S Tosatto, M Pirotta, C d’Eramo, M Restelli
International Conference on Machine Learning, 3434-3443, 2017
302017
Multi-objective reinforcement learning through continuous pareto manifold approximation
S Parisi, M Pirotta, M Restelli
Journal of Artificial Intelligence Research 57, 187-227, 2016
302016
Adaptive batch size for safe policy gradients
M Papini, M Pirotta, M Restelli
The Thirty-first Annual Conference on Neural Information Processing Systems …, 2017
292017
Near optimal exploration-exploitation in non-communicating Markov decision processes
R Fruit, M Pirotta, A Lazaric
arXiv preprint arXiv:1807.02373, 2018
282018
Importance weighted transfer of samples in reinforcement learning
A Tirinzoni, A Sessa, M Pirotta, M Restelli
International Conference on Machine Learning, 4936-4945, 2018
242018
Compatible reward inverse reinforcement learning
A Metelli, M Pirotta, M Restelli
The Thirty-first Annual Conference on Neural Information Processing Systems …, 2017
242017
Manifold-based multi-objective policy search with sample reuse
S Parisi, M Pirotta, J Peters
Neurocomputing 263, 3-14, 2017
242017
Exploration bonus for regret minimization in discrete and continuous average reward mdps
Q Jian, R Fruit, M Pirotta, A Lazaric
22*2019
No-regret exploration in goal-oriented reinforcement learning
J Tarbouriech, E Garcelon, M Valko, M Pirotta, A Lazaric
International Conference on Machine Learning, 9428-9437, 2020
182020
Policy search for the optimal control of Markov Decision Processes: A novel particle-based iterative scheme
G Manganini, M Pirotta, M Restelli, L Piroddi, M Prandini
IEEE transactions on cybernetics 46 (11), 2643-2655, 2015
182015
O sistema não pode executar a operação agora. Tente novamente mais tarde.
Artigos 1–20