Eren Sezener
Eren Sezener
DeepMind
Verified email at google.com - Homepage
Title
Cited by
Cited by
Year
Behaviour suite for reinforcement learning
I Osband, Y Doron, M Hessel, J Aslanides, E Sezener, A Saraiva, ...
International Conference on Learning Representations (ICLR), 2019
362019
Minimal sign representation of Boolean functions: algorithms and exact results for low dimensions
E Sezener, E Oztop
Neural Computation 27 (8), 1796-1823, 2015
72015
Inferring human values for Safe AGI design
E Sezener
Artificial General Intelligence (AGI) 9205, pp 152-155, 2015
62015
Optimizing the depth and the direction of prospective planning using information values
E Sezener, A Dezfouli, M Keramati
PLOS Computational Biology 15 (3), e1006827, 2019
52019
Gated Linear Networks
J Veness, T Lattimore, A Bhoopchand, D Budden, C Mattern, ...
arXiv preprint arXiv:1910.01526, 2019
42019
Online Learning in Contextual Bandits using Gated Linear Networks
E Sezener, M Hutter, D Budden, J Wang, J Veness
NeurIPS 2020, 2020
32020
Optax: Composable gradient transformation and optimisation
M Hessel, D Budden, F Viola, M Rosca, E Sezener, T Hennigan
JAX, 2020
12020
Gaussian Gated Linear Networks
D Budden, A Marblestone, E Sezener, T Lattimore, G Wayne, J Veness
NeurIPS 2020, 2020
2020
Large-scale multilingual audio visual dubbing
Y Yang, B Shillingford, Y Assael, M Wang, W Liu, Y Chen, Y Zhang, ...
arXiv preprint arXiv:2011.03530, 2020
2020
Static and Dynamic Values of Computation in MCTS
E Sezener, P Dayan
Uncertainty in Artificial Intelligence (UAI), 2020
2020
A Combinatorial Perspective on Transfer Learning
J Wang, E Sezener, D Budden, M Hutter, J Veness
Advances in Neural Information Processing Systems 33, 2020
2020
Computing the Value of Computation for Planning
E Sezener
arXiv preprint arXiv:1811.03035, 2018
2018
Algorithms for Obtaining Parsimonious Higher Order Neurons
E Sezener, E Oztop
International Conference on Artificial Neural Networks (ICANN), 146-154, 2017
2017
Approximate planning from better bounds on Q
E Sezener, P Dayan
Reinforcement Learning and Decision Making (RLDM), 2017
2017
The system can't perform the operation now. Try again later.
Articles 1–14