European Commission logo
English English
CORDIS - EU research results
CORDIS

Provably Efficient Algorithms for Large-Scale Reinforcement Learning

Deliverables

Data Management Plan (DMP)

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

Publications

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

Author(s): Gergely Neu, Nneka Okolo
Published in: Proceedings of The 34th International Conference on Algorithmic Learning Theory (ALT 2023), 2023
Publisher: Proceedings of Machine Learning Research

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

Author(s): Gergely Neu, Julia Olkhovskaya, Matteo Papini, Ludovic Schwartz
Published in: Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
Publisher: NeurIPS foundation

Proximal Point Imitation Learning

Author(s): Luca Viano, Angeliki Kamoutsi, Gergely Neu, Igor Krawczuk, Volkan Cevher
Published in: Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
Publisher: NeurIPS foundation

Online learning with off-policy feedback

Author(s): Germano Gabbianelli, Matteo Papini, Gergely Neu
Published in: Proceedings of The 34th International Conference on Algorithmic Learning Theory (ALT 2023), 2023
Publisher: Proceedings of Machine Learning Research

Optimistic Planning by Regularized Dynamic Programming

Author(s): Antoine Moulin, Gergely Neu
Published in: International Conference on Machine Learning (ICML 2022), 2023
Publisher: Proceedings of Machine Learning Research

Generalization bounds via convex analysis

Author(s): Gabor Lugosi, Gergely Neu
Published in: Proceedings of Thirty Fifth Conference on Learning Theory (COLT 2022), 2022
Publisher: Proceedings of Machine Learning Research

Smoothing policies and safe policy gradients

Author(s): Matteo Papini; Matteo Pirotta; Marcello Restelli
Published in: Machine Learning, Issue 111, 2022, Page(s) 4081–4137, ISSN 1573-0565
Publisher: Springer
DOI: 10.1007/s10994-022-06232-6

Searching for OpenAIRE data...

There was an error trying to search data from OpenAIRE

No results available