Folgen
Nadav Merlis
Nadav Merlis
P.hD. candidate, Electrical Engineering, Technion Israel Institute of Technology
Bestätigte E-Mail-Adresse bei campus.technion.ac.il - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Learn what not to learn: Action elimination with deep reinforcement learning
T Zahavy, M Haroush, N Merlis, DJ Mankowitz, S Mannor
arXiv preprint arXiv:1809.02121, 2018
1742018
Tight regret bounds for model-based reinforcement learning with greedy policies
Y Efroni, N Merlis, M Ghavamzadeh, S Mannor
Advances in Neural Information Processing Systems 32, 2019
592019
Batch-size independent regret bounds for the combinatorial multi-armed bandit problem
N Merlis, S Mannor
Conference on Learning Theory, 2465-2489, 2019
162019
Reinforcement learning with trajectory feedback
Y Efroni, N Merlis, S Mannor
Proceedings of the AAAI Conference on Artificial Intelligence 35 (8), 7288-7295, 2021
142021
Ensemble bootstrapping for Q-Learning
O Peer, C Tessler, N Merlis, R Meir
International Conference on Machine Learning, 8454-8463, 2021
122021
Tight lower bounds for combinatorial multi-armed bandits
N Merlis, S Mannor
Conference on Learning Theory, 2830-2857, 2020
112020
Confidence-budget matching for sequential budgeted learning
Y Efroni, N Merlis, A Saha, S Mannor
International Conference on Machine Learning, 2937-2947, 2021
52021
Never Worse, Mostly Better: Stable Policy Improvement in Deep Reinforcement Learning
P Khanna, G Tennenholtz, N Merlis, S Mannor, C Tessler
arXiv e-prints, arXiv: 1910.01062, 2019
4*2019
Lenient regret for multi-armed bandits
N Merlis, S Mannor
Proceedings of the AAAI Conference on Artificial Intelligence 35 (10), 8950-8957, 2021
32021
Reinforcement Learning with a Terminator
G Tennenholtz, N Merlis, L Shani, S Mannor, U Shalit, G Chechik, ...
arXiv preprint arXiv:2205.15376, 2022
2022
Dare not to Ask: Problem-Dependent Guarantees for Budgeted Bandits
N Merlis, Y Efroni, S Mannor
arXiv preprint arXiv:2110.05724, 2021
2021
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–11