James E. Kostas

Reinforcement Learning · 2019

A researcher in the Science corpus: 1 paper; trusts 8 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 19 citations into it
• Artificial Intelligence — 17 citations into it

Whom James E. Kostas trusts overall

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

1. Richard S. Sutton
2. Philip S. Thomas
3. Stefan Schaal
4. Geoffrey E. Hinton
5. Zoubin Ghahramani
6. Vivek Shripad Borkar
7. Andrew Barto
8. Ronald J. Williams
9. Yoshua Bengio
10. Jan Peters

Papers from James E. Kostas's perspective

Ordered by how strongly the researchers James E. Kostas 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. Reinforcement Learning: An Introduction
4. Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
5. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
6. Gradient-based learning applied to document recognition
7. Long Short-Term Memory
8. Attention is All you Need (Neural Information Processing Systems)
9. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
10. ImageNet: A large-scale hierarchical image database

Their papers

• Learning Action Representations for Reinforcement Learning (2019) — 193 citations