Jan Metz

Reinforcement Learning · 2014–2015

A researcher in the Science corpus: 2 papers; trusts 17 researchers and is trusted by 1 researcher here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 35 citations into it; #2,132 of 2,242 by trust here, #1,501 by citations
• Artificial Intelligence — 32 citations into it; #33,169 of 35,345 by trust here, #17,412 by citations
• Control and Systems Engineering — 14 citations into it

Whom Jan Metz trusts overall

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

1. Nathan D. Ratliff
2. Jan Peters
3. W. B. Knox
4. Auke Jan Ijspeert
5. Ashesh Jain
6. Yaakov Engel
7. Brian D. Ziebart
8. Shane Griffith

Who trusts Jan Metz overall

1. Owain Evans

Papers from Jan Metz's perspective

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

1. Maximum Entropy Inverse Reinforcement Learning
2. ImageNet classification with deep convolutional neural networks
3. Reinforcement Learning: An Introduction
4. Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping
5. Gradient-based learning applied to document recognition
6. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
7. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
8. Long Short-Term Memory
9. Maximum margin planning
10. Relative Entropy Policy Search

Their papers

• Active Reward Learning (2014) — 129 citations
• Active reward learning with a novel acquisition function (2015) — 69 citations