Bernhard Hengst

Reinforcement Learning · 2002–2017

A researcher in the Science corpus: 3 papers; trusts 24 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 17 citations into it
• Artificial Intelligence — 7 citations into it

Whom Bernhard Hengst trusts overall

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

1. Richard S. Sutton
2. Doina Precup
3. Thomas G. Dietterich
4. Nils J. Nilsson
5. Andrew Barto
6. George Dimitri Konidaris
7. Ronald E. Parr
8. Christopher J. C. H. Watkins
9. Peter S. Dayan
10. David Andre

Who trusts Bernhard Hengst overall

1. Andrew Barto
2. George Dimitri Konidaris
3. Özgür Simsek
4. Marlos C. Machado
5. Matthew Botvinick
6. Sridhar Mahadevan
7. Michael H. Bowling
8. William T. B. Uther
9. Yael Niv
10. Sanjay Krishnan

Papers from Bernhard Hengst's perspective

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

1. ImageNet classification with deep convolutional neural networks
2. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
3. Reinforcement Learning: An Introduction
4. Gradient-based learning applied to document recognition
5. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
6. Long Short-Term Memory
7. Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning
8. Attention is All you Need (Neural Information Processing Systems)
9. Learning Multiple Layers of Features from Tiny Images
10. Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Their papers

• Hierarchical Approaches (2012) — 29 citations
• Encyclopedia of Machine Learning and Data Mining (2017) — 452 citations
• Discovering Hierarchy in Reinforcement Learning with HEXQ (2002) — 246 citations