Segui
Jelena Luketina
Jelena Luketina
Email verificata su cs.ox.ac.uk
Titolo
Citata da
Citata da
Anno
Progress & compress: A scalable framework for continual learning
J Schwarz, W Czarnecki, J Luketina, A Grabska-Barwinska, YW Teh, ...
International conference on machine learning, 4528-4537, 2018
5832018
A survey of reinforcement learning informed by natural language
J Luketina, N Nardelli, G Farquhar, J Foerster, J Andreas, E Grefenstette, ...
arXiv preprint arXiv:1906.03926, 2019
1922019
Scalable gradient-based tuning of continuous regularization hyperparameters
J Luketina, M Berglund, K Greff, T Raiko
International conference on machine learning, 2952-2960, 2016
1572016
Transient non-stationarity and generalisation in deep reinforcement learning
M Igl, G Farquhar, J Luketina, W Boehmer, S Whiteson
arXiv preprint arXiv:2006.05826, 2020
362020
The impact of non-stationarity on generalisation in deep reinforcement learning
M Igl, G Farquhar, J Luketina, W Boehmer, S Whiteson
arXiv preprint arXiv:2006.05826, 2020
202020
Wordcraft: An environment for benchmarking commonsense agents
M Jiang, J Luketina, N Nardelli, P Minervini, PHS Torr, S Whiteson, ...
arXiv preprint arXiv:2007.09185, 2020
172020
On the impossibility of supersized machines
B Garfinkel, M Brundage, D Filan, C Flynn, J Luketina, M Page, ...
arXiv preprint arXiv:1703.10987, 2017
42017
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
32022
Learning Skills Diverse in Value-Relevant Features
MJA Smith, J Luketina, K Hartikainen, M Igl, S Whiteson
Conference on Lifelong Learning Agents, 1174-1194, 2022
2022
Neural networks for scalable continual learning in domains with sequentially learned tasks
J Schwarz, R Pascanu, RT Hadsell, W Czarnecki, YW Teh, J Luketina
US Patent App. 17/048,023, 2021
2021
Il sistema al momento non pu eseguire l'operazione. Riprova pi tardi.
Articoli 1–10