Yonathan Efroni
Yonathan Efroni
Microsoft Research, New York
Zweryfikowany adres z microsoft.com - Strona główna
Tytuł
Cytowane przez
Cytowane przez
Rok
Adaptive trust region policy optimization: Global convergence and faster rates for regularized mdps
L Shani, Y Efroni, S Mannor
Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 5668-5675, 2020
602020
Action Robust Reinforcement Learning and Applications in Continuous Control
C Tessler, Y Efroni, S Mannor
arXiv preprint arXiv:1901.09184, 2019
482019
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, 12203-12213, 2019
372019
Exploration-exploitation in constrained mdps
Y Efroni, S Mannor, M Pirotta
arXiv preprint arXiv:2003.02189, 2020
342020
Optimistic policy optimization with bandit feedback
L Shani, Y Efroni, A Rosenberg, S Mannor
International Conference on Machine Learning, 8604-8613, 2020
29*2020
Universality of local weak interactions and its application for interferometric alignment
J Dziewior, L Knips, D Farfurnik, K Senkalla, N Benshalom, J Efroni, ...
Proceedings of the National Academy of Sciences 116 (8), 2881-2890, 2019
272019
Beyond the one-step greedy approach in reinforcement learning
Y Efroni, G Dalal, B Scherrer, S Mannor
International Conference on Machine Learning, 1387-1396, 2018
252018
Multiple-step greedy policies in approximate and online reinforcement learning
Y Efroni, G Dalal, B Scherrer, S Mannor
NeurIPS, 2018
17*2018
How to combine tree-search methods in reinforcement learning
Y Efroni, G Dalal, B Scherrer, S Mannor
Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 3494-3501, 2019
132019
Mirror descent policy optimization
M Tomar, L Shani, Y Efroni, M Ghavamzadeh
arXiv preprint arXiv:2005.09814, 2020
122020
Topological transitions and fractional charges induced by strain and a magnetic field in carbon nanotubes
Y Efroni, S Ilani, E Berg
Physical review letters 119 (14), 147704, 2017
102017
Online Planning with Lookahead Policies
Y Efroni, M Ghavamzadeh, S Mannor
Advances in Neural Information Processing Systems 33, 2020
8*2020
Exploration conscious reinforcement learning revisited
L Shani, Y Efroni, S Mannor
International Conference on Machine Learning, 5680-5689, 2019
8*2019
Minimax regret for stochastic shortest path
A Cohen, Y Efroni, Y Mansour, A Rosenberg
arXiv preprint arXiv:2103.13056, 2021
42021
Reinforcement learning with trajectory feedback
Y Efroni, N Merlis, S Mannor
arXiv preprint arXiv:2008.06036, 2020
42020
Confidence-budget matching for sequential budgeted learning
Y Efroni, N Merlis, A Saha, S Mannor
arXiv preprint arXiv:2102.03400, 2021
22021
RL for Latent MDPs: Regret Guarantees and a Lower Bound
J Kwon, Y Efroni, C Caramanis, S Mannor
arXiv preprint arXiv:2102.04939, 2021
12021
Multi-step Greedy Reinforcement Learning Algorithms
M Tomar, Y Efroni, M Ghavamzadeh
International Conference on Machine Learning, 9504-9513, 2020
1*2020
Training Deep Neural Networks by optimizing over nonlocal paths in hyperparameter space
V Pushkarov, J Efroni, M Maksymenko, M Koch-Janusz
arXiv preprint arXiv:1909.04013, 2019
12019
Bandits with Partially Observable Offline Data
G Tennenholtz, U Shalit, S Mannor, Y Efroni
arXiv preprint arXiv:2006.06731, 2020
2020
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–20