Følg
Sebastian Flennerhag
Sebastian Flennerhag
Research Scientist at DeepMind
Verifisert e-postadresse på google.com - Startside
Tittel
Sitert av
Sitert av
År
Meta-learning with warped gradient descent
S Flennerhag, AA Rusu, R Pascanu, F Visin, H Yin, R Hadsell
arXiv preprint arXiv:1909.00025, 2019
2512019
Bootstrapped meta-learning
S Flennerhag, Y Schroecker, T Zahavy, H van Hasselt, D Silver, S Singh
arXiv preprint arXiv:2109.04504, 2021
772021
Transferring Knowledge across Learning Processes
S Flennerhag, PG Moreno, ND Lawrence, A Damianou
Seventh International Conference on Learning Representations, 2019
752019
Discovering evolution strategies via meta-black-box optimization
R Lange, T Schaul, Y Chen, T Zahavy, V Dalibard, C Lu, S Singh, ...
Proceedings of the Companion Conference on Genetic and Evolutionary …, 2023
472023
Discovering policies with domino: Diversity optimization maintaining near optimality
T Zahavy, Y Schroecker, F Behbahani, K Baumli, S Flennerhag, S Hou, ...
arXiv preprint arXiv:2205.13521, 2022
402022
Introducing symmetries to black box meta reinforcement learning
L Kirsch, S Flennerhag, H Van Hasselt, A Friesen, J Oh, Y Chen
Proceedings of the AAAI Conference on Artificial Intelligence 36 (7), 7202-7210, 2022
342022
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
312023
Augmenting correlation structures in spatial data using deep generative models
K Klemmer, A Koshiyama, S Flennerhag
arXiv preprint arXiv:1905.09796, 2019
292019
Reload: Reinforcement learning with optimistic ascent-descent for last-iterate convergence in constrained mdps
T Moskovitz, B O’Donoghue, V Veeriah, S Flennerhag, S Singh, T Zahavy
International Conference on Machine Learning, 25303-25336, 2023
202023
Vision-language models as a source of rewards
K Baumli, S Baveja, F Behbahani, H Chan, G Comanici, S Flennerhag, ...
arXiv preprint arXiv:2312.09187, 2023
182023
Discovering diverse nearly optimal policies with successor features
T Zahavy, B O'Donoghue, A Barreto, V Mnih, S Flennerhag, S Singh
arXiv preprint arXiv:2106.00669, 2021
182021
Temporal difference uncertainties as a signal for exploration
S Flennerhag, JX Wang, P Sprechmann, F Visin, A Galashov, ...
arXiv preprint arXiv:2010.02255, 2020
162020
Quantnet: Transferring learning across systematic trading strategies
A Koshiyama, S Flennerhag, SB Blumberg, N Firoozye, P Treleaven
arXiv preprint arXiv:2004.03445, 2020
16*2020
Breaking the activation function bottleneck through adaptive parameterization
S Flennerhag, H Yin, J Keane, M Elliot
Advances in Neural Information Processing Systems 31, 2018
152018
Meta-gradients in non-stationary environments
J Luketina, S Flennerhag, Y Schroecker, D Abel, T Zahavy, S Singh
Conference on Lifelong Learning Agents, 886-901, 2022
102022
Probing transfer in deep reinforcement learning without task engineering
AA Rusu, S Flennerhag, D Rao, R Pascanu, R Hadsell
Conference on Lifelong Learning Agents, 1231-1254, 2022
72022
Optimistic meta-gradients
S Flennerhag, T Zahavy, B O'Donoghue, HP van Hasselt, A György, ...
Advances in Neural Information Processing Systems 36, 2024
32024
Towards Scalable Meta-Learning
S Flennerhag
PQDT-Global, 2021
22021
Optimism and Adaptivity in Policy Optimization
V Chelu, T Zahavy, A Guez, D Precup, S Flennerhag
arXiv preprint arXiv:2306.10587, 2023
2023
Discovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization
R Tjarko Lange, T Schaul, Y Chen, C Lu, T Zahavy, V Dalibard, ...
arXiv e-prints, arXiv: 2304.03995, 2023
2023
Systemet kan ikke utføre handlingen. Prøv på nytt senere.
Artikler 1–20