Seguir
Marcin Moczulski
Marcin Moczulski
Google AI, University of Oxford
Dirección de correo verificada de stcatz.ox.ac.uk
Título
Citado por
Citado por
Año
Noisy activation functions
C Gulcehre, M Moczulski, M Denil, Y Bengio
Published at ICML 2016 (International conference on machine learning), 3059-3068, 2016
3612016
Deep fried convnets
Z Yang, M Moczulski, M Denil, N de Freitas, A Smola, L Song, Z Wang
Oral presentation at ICCV 2015 (Proceedings of the IEEE International …, 2015
3582015
Acdc: A structured efficient linear layer
M Moczulski, M Denil, J Appleyard, N de Freitas
Published at ICLR 2016 (International Conference on Learning Representations), 2015
1272015
Contingency-Aware Exploration in Reinforcement Learning
J Choi, Y Guo, ML Moczulski, J Oh, N Wu, M Norouzi, H Lee
Published at ICLR 2019, 2019
952019
Mollifying networks
C Gulcehre, M Moczulski, F Visin, Y Bengio
Published at ICLR 2017, 2016
642016
Memory based trajectory-conditioned policies for learning from sparse rewards
Y Guo, J Choi, M Moczulski, S Feng, S Bengio, M Norouzi, H Lee
Advances in Neural Information Processing Systems 33, 4333-4345, 2020
44*2020
A robust adaptive stochastic gradient method for deep learning
C Gulcehre, J Sotelo, M Moczulski, Y Bengio
2017 International Joint Conference on Neural Networks (IJCNN), 125-132, 2017
272017
Adasecant: Robust adaptive secant method for stochastic gradient
C Gulcehre, M Moczulski, Y Bengio
Published at IJCNN 2017, 2014
252014
Efficient exploration with self-imitation learning via trajectory-conditioned policy
Y Guo, J Choi, M Moczulski, S Bengio, M Norouzi, H Lee
arXiv preprint arXiv:1907.10247, 2019
112019
Sparsedice: Imitation learning for temporally sparse data via regularization
A Camacho, I Gur, ML Moczulski, O Nachum, A Faust
ICML 2021 Workshop on Unsupervised Reinforcement Learning, 2021
52021
A Controller-Recognizer Framework: How necessary is recognition for control?
M Moczulski, K Xu, A Courville, K Cho
Published at ICLR 2016 workshop, 2015
22015
El sistema no puede realizar la operación en estos momentos. Inténtalo de nuevo más tarde.
Artículos 1–11