Urmăriți
Jesse Farebrother
Jesse Farebrother
Mila / McGill University; Google DeepMind
Adresă de e-mail confirmată pe cs.mcgill.ca - Pagina de pornire
Titlu
Citat de
Citat de
Anul
Generalization and Regularization in DQN
J Farebrother, MC Machado, M Bowling
NeurIPS Workshop on Deep Reinforcement Learning, 2018
1852018
Investigating Multi-task Pretraining and Generalization in Reinforcement Learning
AA Taïga, R Agarwal, J Farebrother, A Courville, MG Bellemare
International Conference on Learning Representations (ICLR), 2023
142023
Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks
J Farebrother*, J Greaves*, R Agarwal, C Le Lan, R Goroshin, PS Castro, ...
International Conference on Learning Representations (ICLR), 2023
13*2023
A Novel Stochastic Gradient Descent Algorithm for Learning Principal Subspaces
CL Lan, J Greaves, J Farebrother, M Rowland, F Pedregosa, R Agarwal, ...
International Conference on Artificial Intelligence and Statistics (AISTATS), 2023
32023
Mixtures of Experts Unlock Parameter Scaling for Deep RL
J Obando-Ceron*, G Sokar*, T Willi*, C Lyle, J Farebrother, J Foerster, ...
arXiv preprint arXiv:2402.08609, 2024
22024
Learning and Controlling Silicon Dopant Transitions in Graphene using Scanning Transmission Electron Microscopy
M Schwarzer*, J Farebrother*, J Greaves, ED Cubuk, R Agarwal, ...
arXiv preprint arXiv:2311.17894, 2023
2*2023
Stop Regressing: Training Value Functions via Classification for Scalable Deep RL
J Farebrother, J Orbay, Q Vuong, AA Taïga, Y Chebotar, T Xiao, A Irpan, ...
arXiv preprint arXiv:2403.03950, 2024
12024
A Distributional Analogue to the Successor Representation
H Wiltzer*, J Farebrother*, A Gretton, Y Tang, A Barreto, W Dabney, ...
arXiv preprint arXiv:2402.08530, 2024
2024
Using biconnected components for efficient identification of upstream features in large spatial networks (GIS cup)
Z Goldthorpe, J Cannon, J Farebrother, Z Friggstad, MA Nascimento
Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances …, 2018
2018
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–9