Matej Vecerík

Reinforcement Learning · 2016–2018

A researcher in the Science corpus: 6 papers; trusts 50 researchers and is trusted by 23 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 131 citations into it; #857 of 2,242 by trust here, #224 by citations
• Artificial Intelligence — 111 citations into it; #8,316 of 35,345 by trust here, #2,219 by citations
• Control and Systems Engineering — 43 citations into it; #7,507 of 8,257 by trust here, #423 by citations
• Robotics & Control — 22 citations into it
• Computational Theory and Mathematics — 16 citations into it
• Management Science and Operations Research — 14 citations into it
• Optimization & Training — 11 citations into it
• Mechanical Engineering — 5 citations into it

Whom Matej Vecerík trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Sergey Levine
2. E. Todorov
3. Volodymyr Mnih
4. Richard S. Sutton
5. Diederik P. Kingma
6. Chelsea Finn
7. Geoffrey E. Hinton
8. Pieter Abbeel
9. Mohit Sewak
10. David Silver

Who trusts Matej Vecerík overall

1. Sergey Levine
2. Ashvin Nair
3. Scott Fujimoto
4. Pieter Abbeel
5. Abhishek Gupta
6. Mel Vecerík
7. Henry Zhu
8. Yuxi Li
9. T. Paine
10. Aravind Rajeswaran

Papers from Matej Vecerík's perspective

Ordered by how strongly the researchers Matej Vecerík trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Long Short-Term Memory
5. Gradient-based learning applied to document recognition
6. Attention is All you Need (Neural Information Processing Systems)
7. ImageNet: A large-scale hierarchical image database
8. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
9. Learning Multiple Layers of Features from Tiny Images
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• Sim-to-Real Robot Learning from Pixels with Progressive Nets (2016) — 568 citations
• Deep Q-learning From Demonstrations (2017) — 1,289 citations
• Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards (2017) — 764 citations
• Data-efficient Deep Reinforcement Learning for Dexterous Manipulation (2017) — 285 citations
• Learning from Demonstrations for Real World Reinforcement Learning (2017) — 160 citations
• Safe Exploration in Continuous Action Spaces (2018) — 522 citations