The Description Length of Deep Learning Models L Blier, Y Ollivier Advances in Neural Information Processing Systems, 2216--2226, 2018 | 87 | 2018 |
Making Deep Q-learning methods robust to time discretization C Tallec, L Blier, Y Ollivier International Conference of Machine Learning, 2019 | 86 | 2019 |
Learning Successor States and Goal-Dependent Values: A Mathematical Viewpoint L Blier, C Tallec, Y Ollivier arXiv preprint arXiv:2101.07123, 2021 | 23 | 2021 |
Learning with Random Learning Rates L Blier, P Wolinski, Y Ollivier European Conference of Machine Learning, 2019 | 22 | 2019 |
Unbiased Methods for Multi-Goal Reinforcement Learning L Blier, Y Ollivier arXiv preprint arXiv:2106.08863, 2021 | 7 | 2021 |
Reproducing" World Models" Is training the recurrent network really needed L Blier, C Kalainathan, Diviyanm Tallec https://ctallec.github.io/world-models/, 2018 | 7 | 2018 |
Some Principled Methods for Deep Reinforcement Learning L Blier Université Paris-Saclay, Inria, Facebook AI Research, 2022 | | 2022 |
An overview of my thesis: Some Principled Methods for Deep Reinforcement Learning L Blier | | |