Steven J. Bradtke

Reinforcement Learning · 1995–2004

A researcher in the Science corpus: 2 papers; trusts 12 researchers and is trusted by 194 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 17 citations into it; #133 of 2,242 by trust here, #603 by citations
• Optimization & Training — 6 citations into it

Whom Steven J. Bradtke trusts overall

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

1. Richard S. Sutton
2. Paul J. Werbos
3. Peter S. Dayan
4. John N. Tsitsiklis
5. G. Tesauro
6. Ben J. A. Kröse
7. Christopher J. C. H. Watkins
8. Dimitri P. Bertsekas
9. Andrew Barto
10. Andrew W. Moore

Who trusts Steven J. Bradtke overall

1. Huizhen Yu
2. Dimitri P. Bertsekas
3. Csaba Szepesvari
4. Richard S. Sutton
5. Amir-massoud Farahmand
6. Bruno Scherrer
7. J. Urgen Schmidhuber
8. Matthieu Geist
9. Hado van Hasselt
10. Philip S. Thomas

Papers from Steven J. Bradtke's perspective

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

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Gradient-based learning applied to document recognition
4. Long Short-Term Memory
5. Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
6. Reinforcement Learning: An Introduction
7. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
8. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
9. Learning to predict by the methods of temporal differences
10. Learning Multiple Layers of Features from Tiny Images

Their papers

• Linear Least-Squares algorithms for temporal difference learning (2004) — 798 citations
• Learning to Act Using Real-Time Dynamic Programming (1995)