Aleksandr Fedorov

Reinforcement Learning · 2015

A researcher in the Science corpus: 1 paper; trusts 3 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 8 citations into it
• Computer Vision and Pattern Recognition — 6 citations into it

Whom Aleksandr Fedorov trusts overall

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

1. Ronald J. Williams
2. Volodymyr Mnih

Papers from Aleksandr Fedorov's perspective

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

1. Long Short-Term Memory
2. Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
3. Human-level control through deep reinforcement learning
4. Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
5. ImageNet classification with deep convolutional neural networks
6. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
7. Gradient-based learning applied to document recognition
8. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
9. Policy Gradient Methods for Reinforcement Learning with Function Approximation
10. Recurrent Models of Visual Attention

Their papers

• Deep Attention Recurrent Q-Network (2015) — 170 citations