Следене
Tom Zahavy
Tom Zahavy
Други именаTom Ben Zion Zahavy
Staff Research Scientist, Google DeepMind
Потвърден имейл адрес: deepmind.com - Начална страница
Заглавие
Позовавания
Позовавания
Година
A deep hierarchical approach to lifelong learning in minecraft
C Tessler, S Givony, T Zahavy, D Mankowitz, S Mannor
Proceedings of the AAAI conference on artificial intelligence 31 (1), 2017
4642017
Graying the black box: Understanding dqns
T Zahavy, N Ben-Zrihem, S Mannor
International conference on machine learning (ICML), 1899-1908, 2016
3422016
Learn what not to learn: Action elimination with deep reinforcement learning
T Zahavy, M Haroush, N Merlis, DJ Mankowitz, S Mannor
Advances in neural information processing systems 31, 2018
2522018
Deep learning reconstruction of ultrashort pulses
T Zahavy, A Dikopoltsev, D Moss, GI Haham, O Cohen, S Mannor, ...
Optica 5 (5), 666-673, 2018
1772018
Is a picture worth a thousand words? A deep multi-modal architecture for product classification in e-commerce
T Zahavy, A Krishnan, A Magnani, S Mannor
Proceedings of the AAAI conference on artificial intelligence 32 (1), 2018
105*2018
A self-tuning actor-critic algorithm
T Zahavy, Z Xu, V Veeriah, M Hessel, J Oh, HP van Hasselt, D Silver, ...
Advances in neural information processing systems 33, 20913-20924, 2020
862020
Bootstrapped meta-learning
S Flennerhag, Y Schroecker, T Zahavy, H van Hasselt, D Silver, S Singh
International Conference on Learning Representations (ICLR) 2022, 2021
722021
Reward is enough for convex mdps
T Zahavy, B O'Donoghue, G Desjardins, S Singh
Advances in Neural Information Processing Systems 34, 25746-25759, 2021
702021
Shallow updates for deep reinforcement learning
N Levine, T Zahavy, DJ Mankowitz, A Tamar, S Mannor
Advances in Neural Information Processing Systems 30, 2017
512017
Online limited memory neural-linear bandits with likelihood matching
O Nabati, T Zahavy, S Mannor
International Conference on Machine Learning, 7905-7915, 2021
46*2021
Discovering Evolution Strategies via Meta-Black-Box Optimization
R Tjarko Lange, T Schaul, Y Chen, T Zahavy, V Dallibard, C Lu, S Singh, ...
International Conference on Learning Representations (ICLR) 2023, 2022
41*2022
Discovery of options via meta-learned subgoals
V Veeriah, T Zahavy, M Hessel, Z Xu, J Oh, I Kemaev, HP van Hasselt, ...
Advances in Neural Information Processing Systems 34, 29861-29873, 2021
392021
Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality
T Zahavy, Y Schroecker, F Behbahani, K Baumli, S Flennerhag, S Hou, ...
International Conference on Learning Representations (ICLR) 2023, 2022
342022
Ensemble robustness and generalization of stochastic deep learning algorithms
T Zahavy, B Kang, A Sivak, J Feng, H Xu, S Mannor
arXiv preprint arXiv:1602.02389, 2016
34*2016
Deep learning reconstruction of ultrashort pulses from 2D spatial intensity patterns recorded by an all-in-line system in a single-shot
R Ziv, A Dikopoltsev, T Zahavy, I Rubinstein, P Sidorenko, O Cohen, ...
Optics express 28 (5), 7528-7538, 2020
292020
Discovering attention-based genetic algorithms via meta-black-box optimization
R Lange, T Schaul, Y Chen, C Lu, T Zahavy, V Dalibard, S Flennerhag
Proceedings of the Genetic and Evolutionary Computation Conference, 929-937, 2023
272023
Online Apprenticeship Learning
L Shani, T Zahavy, S Mannor
Proceedings of the AAAI Conference on Artificial Intelligence, 2021
272021
Balancing constraints and rewards with meta-gradient d4pg
DA Calian, DJ Mankowitz, T Zahavy, Z Xu, J Oh, N Levine, T Mann
International Conference on Learning Representations (ICLR) 2021, 2020
252020
Emphatic algorithms for deep reinforcement learning
R Jiang, T Zahavy, Z Xu, A White, M Hessel, C Blundell, H Van Hasselt
International Conference on Machine Learning (ICML), 5023-5033, 2021
232021
Discovering a set of policies for the worst case reward
T Zahavy, A Barreto, DJ Mankowitz, S Hou, B O'Donoghue, I Kemaev, ...
International Conference on Learning Representations (ICLR) 2021, 2021
232021
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–20