Nate Kohl

Artificial Intelligence · 2003–2005

A researcher in the Science corpus: 4 papers; trusts 6 researchers and is trusted by 179 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 16 citations into it; #1,546 of 35,345 by trust here, #6,468 by citations
• Reinforcement Learning — 13 citations into it; #223 of 2,242 by trust here, #716 by citations

Whom Nate Kohl trusts overall

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

1. Faustino J. Gomez
2. Peter Stone
3. Risto Miikkulainen
4. Richard S. Sutton
5. Ben J. A. Kröse
6. Kenneth O. Stanley
7. Mark J van Rossum
8. David E. Moriarty
9. L. D. Whitley
10. Geoffrey E. Hinton

Who trusts Nate Kohl overall

1. J. Urgen Schmidhuber
2. Sergey Levine
3. Pieter Abbeel
4. Chelsea Finn
5. Jan Peters
6. Shimon Whiteson
7. Yoshua Bengio
8. Trevor Darrell
9. Shixiang Shane Gu
10. Andras Gabor Kupcsik

Papers from Nate Kohl's perspective

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

1. ImageNet classification with deep convolutional neural networks
2. Gradient-based learning applied to document recognition
3. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
4. Long Short-Term Memory
5. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
6. Policy Gradient Methods for Reinforcement Learning with Function Approximation
7. ImageNet: A large-scale hierarchical image database
8. Learning Multiple Layers of Features from Tiny Images
9. Reinforcement Learning: A Survey
10. Attention is All you Need (Neural Information Processing Systems)

Their papers

• Policy gradient reinforcement learning for fast quadrupedal locomotion (2004) — 671 citations
• Evolving Keepaway Soccer Players through Task Decomposition (2003) — 112 citations
• Evolving Soccer Keepaway Players Through Task Decomposition (2005) — 92 citations
• Reinforcement Learning Benchmarks and Bake-offs II A workshop at the 2005 NIPS conference (2005)