Jan Matas
Reinforcement Learning · 2018
A researcher in the Science corpus: 1 paper; trusts 11 researchers and is trusted by 12 researchers here, as inferred from the citation graph.
Subfields
- Reinforcement Learning — 17 citations into it; #1,136 of 2,242 by trust here, #1,501 by citations
- Artificial Intelligence — 15 citations into it; #14,458 of 35,345 by trust here, #17,412 by citations
- Control and Systems Engineering — 13 citations into it; #2,683 of 8,257 by trust here, #2,528 by citations
Whom Jan Matas trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Pieter Abbeel
- Tom Schaul
- Timothy P. Lillicrap
- Shixiang Shane Gu
- Richard S. Sutton
- Xue Bin Peng
- Sergey Levine
- Geoffrey E. Hinton
- John Schulman
- Diederik P. Kingma
Who trusts Jan Matas overall
- Stephen James
- Daniel Seita
- Xingyu Lin
- Wenshuai Zhao
- Hang Yin
- Ofir Nachum
- Daniel E. Ho
- Chen Tang
- Li Chen
- Kalifou René Traoré
Papers from Jan Matas's perspective
Ordered by how strongly the researchers Jan Matas trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- Sim-to-Real Reinforcement Learning for Deformable Object Manipulation (2018) — 424 citations