Provably Efficient Algorithms for Large-Scale Reinforcement Learning

Rezultaty

The Open Research Data Pilot will be prepared and submitted to the European Commission

Publikacje

Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization

Autorzy: Gergely Neu, Nneka Okolo
Opublikowane w: Proceedings of The 34th International Conference on Algorithmic Learning Theory (ALT 2023), 2023
Wydawca: Proceedings of Machine Learning Research

Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits

Autorzy: Gergely Neu, Julia Olkhovskaya, Matteo Papini, Ludovic Schwartz
Opublikowane w: Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
Wydawca: NeurIPS foundation

Proximal Point Imitation Learning

Autorzy: Luca Viano, Angeliki Kamoutsi, Gergely Neu, Igor Krawczuk, Volkan Cevher
Opublikowane w: Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
Wydawca: NeurIPS foundation

Online learning with off-policy feedback

Autorzy: Germano Gabbianelli, Matteo Papini, Gergely Neu
Opublikowane w: Proceedings of The 34th International Conference on Algorithmic Learning Theory (ALT 2023), 2023
Wydawca: Proceedings of Machine Learning Research

Optimistic Planning by Regularized Dynamic Programming

Autorzy: Antoine Moulin, Gergely Neu
Opublikowane w: International Conference on Machine Learning (ICML 2022), 2023
Wydawca: Proceedings of Machine Learning Research

Generalization bounds via convex analysis

Autorzy: Gabor Lugosi, Gergely Neu
Opublikowane w: Proceedings of Thirty Fifth Conference on Learning Theory (COLT 2022), 2022
Wydawca: Proceedings of Machine Learning Research

Smoothing policies and safe policy gradients

Autorzy: Matteo Papini; Matteo Pirotta; Marcello Restelli
Opublikowane w: Machine Learning, Numer 111, 2022, Strona(/y) 4081–4137, ISSN 1573-0565
Wydawca: Springer
DOI: 10.1007/s10994-022-06232-6

Rezultaty

Publikacje

Udostępnij tę stronę

Pobierz