Peter Sunehag

Reinforcement Learning · 2009–2018

A researcher in the Science corpus: 6 papers; trusts 21 researchers and is trusted by 12 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 78 citations into it; #1,544 of 2,242 by trust here, #738 by citations
• Artificial Intelligence — 62 citations into it; #13,787 of 35,345 by trust here, #6,569 by citations
• Management Science and Operations Research — 17 citations into it; #7,499 of 11,946 by trust here, #6,024 by citations
• Computational Theory and Mathematics — 13 citations into it; #6,509 of 12,182 by trust here, #6,165 by citations
• Optimization & Training — 10 citations into it; #1,948 of 2,601 by trust here, #2,162 by citations
• Control and Systems Engineering — 7 citations into it
• Statistical Learning Theory — 7 citations into it
• Electrical and Electronic Engineering — 5 citations into it

Whom Peter Sunehag trusts overall

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

1. N. Schraudolph
2. Shun-ichi Amari
3. Andrew Barto
4. Martin A. Zinkevich
5. Richard S. Sutton
6. Martin L. Puterman
7. Michael L. Littman
8. Diederik P. Kingma
9. Matthew J. Hausknecht
10. van der D David Pol

Who trusts Peter Sunehag overall

1. Mark W. Schmidt
2. Tabish Rashid
3. Georgios Papoudakis
4. Christian Schröder de Witt
5. Tonghan Wang
6. Jiachen Yang
7. Filippos Christianos
8. Hengyuan Hu
9. Sai Qian Zhang
10. Jianhao Wang

Papers from Peter Sunehag's perspective

Ordered by how strongly the researchers Peter Sunehag 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. Reinforcement Learning: An Introduction
7. Attention is All you Need (Neural Information Processing Systems)
8. ImageNet: A large-scale hierarchical image database
9. Learning Multiple Layers of Features from Tiny Images
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Deep Reinforcement Learning in Large Discrete Action Spaces (2015) — 640 citations
• The Sample-Complexity of General Reinforcement Learning (2013) — 73 citations
• Variable Metric Stochastic Approximation Theory (2009) — 32 citations
• Malthusian Reinforcement Learning (2018) — 43 citations
• Value-Decomposition Networks For Cooperative Multi-Agent Learning Based On Team Reward (2018) — 895 citations
• Value-Decomposition Networks For Cooperative Multi-Agent Learning (2017) — 1,350 citations