Provably Efficient Algorithms for Large-Scale Reinforcement Learning

Información del proyecto

SCALER

Identificador del acuerdo de subvención: 950180

DOI

10.3030/950180

Fecha de la firma de la CE 3 Septiembre 2020

Fecha de inicio 1 Octubre 2021

Fecha de finalización 30 Septiembre 2026

Financiado con arreglo a

• EXCELLENT SCIENCE - European Research Council (ERC)

Coste total

€ 1 493 990,00

Aportación de la UE

€ 1 493 990,00

Coordinado por

UNIVERSIDAD POMPEU FABRA
Spain

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Resultado final

Open Research Data Pilot (1)

Data Management Plan (DMP)

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

Publicaciones

Conference proceedings (14)

Offline Primal-Dual Reinforcement Learning for Linear MDPs

Autores: G. Gabbianelli, G. Neu, N. Okolo, M. Papini
Publicado en: Proceedings of the Twenty-seventh International Conference on Artificial Intelligence and Statistics (AISTATS), 2024
Editor: Proceedings of Machine Learning Research

Scalable Representation Learning in Linear Contextual Bandits with Constant Regret Guarantees

Autores: Tirinzoni A.; Papini M.; Touati A.; Lazaric A.; Pirotta M.
Publicado en: Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
Editor: NeurIPS foundation
DOI: 10.48550/arxiv.2210.13083

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

Autores: Gergely Neu, Nneka Okolo
Publicado en: Proceedings of The 34th International Conference on Algorithmic Learning Theory (ALT 2023), 2023
Editor: Proceedings of Machine Learning Research

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

Autores: Gergely Neu, Julia Olkhovskaya, Matteo Papini, Ludovic Schwartz
Publicado en: Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
Editor: NeurIPS foundation

Nonstochastic Contextual Combinatorial Bandits

Autores: L. Zierahn, D. van der Hoeven, N. Cesa-Bianchi, G. Neu
Publicado en: Proceedings of the Twenty-sixth International Conference on Artificial Intelligence and Statistics (AISTATS), 2023
Editor: Proceedings of Machine Learning Research

Optimistic Information-Directed Sampling

Autores: G. Neu, M. Papini, L. Schwartz
Publicado en: Proceedings of the 36th Annual Conference on Learning Theory (COLT), 2024
Editor: Proceedings of Machine Learning Research

Dealing with Unbounded Gradients in Stochastic Saddle-Point Optimizaiton

Autores: G. Neu, N. Okolo
Publicado en: Proceedings of the 41st International Conference on Machine Learning (ICML), 2024
Editor: Proceedings of Machine Learning Research

Proximal Point Imitation Learning

Autores: Luca Viano, Angeliki Kamoutsi, Gergely Neu, Igor Krawczuk, Volkan Cevher
Publicado en: Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
Editor: NeurIPS foundation

Importance-Weighted Offline Learning Done Right

Autores: G. Gabbianelli, G. Neu, M. Papini
Publicado en: Proceedings of the 34th International Conference on Algorithmic Learning Theory (ALT), 2024
Editor: Proceedings of Machine Learning Research

Online learning with off-policy feedback

Autores: Germano Gabbianelli, Matteo Papini, Gergely Neu
Publicado en: Proceedings of The 34th International Conference on Algorithmic Learning Theory (ALT 2023), 2023
Editor: Proceedings of Machine Learning Research

First-and Second-Order Bounds for Adversarial Linear Contextual Bandits

Autores: J. Olkhovskaya, J. Mayo, T. van Erven, G. Neu, C.-Y. Wei
Publicado en: Advances in Neural Information Processing Systems 36 (NeurIPS), 2023
Editor: NeurIPS foundation

Optimistic Planning by Regularized Dynamic Programming

Autores: Antoine Moulin, Gergely Neu
Publicado en: International Conference on Machine Learning (ICML 2022), 2023
Editor: Proceedings of Machine Learning Research

Generalization bounds via convex analysis

Autores: Gabor Lugosi, Gergely Neu
Publicado en: Proceedings of Thirty Fifth Conference on Learning Theory (COLT 2022), 2022
Editor: Proceedings of Machine Learning Research

Adversarial Contextual Bandits Go Kernelized

Autores: G. Neu, J. Olkhovskaya, S. Vakili
Publicado en: Proceedings of the 34th International Conference on Algorithmic Learning Theory (ALT), 2024
Editor: Proceedings of Machine Learning Research

Peer reviewed articles (2)

Smoothing policies and safe policy gradients

Autores: Matteo Papini; Matteo Pirotta; Marcello Restelli
Publicado en: Machine Learning, Edición 111, 2022, Página(s) 4081–4137, ISSN 1573-0565
Editor: Springer
DOI: 10.1007/s10994-022-06232-6

A note on regularised NTK dynamics with an application to PAC-Bayesian training

Autores: Clerico, Eugenio; Guedj, Benjamin
Publicado en: Transactions on Machine Learning Research, 2024, ISSN 2835-8856
Editor: Transactions on Machine Learning Research
DOI: 10.48550/arxiv.2312.13259