Makoto Otsuka

Reinforcement Learning · 2010–2014

A researcher in the Science corpus: 4 papers; trusts 17 researchers and is trusted by 1 researcher here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 7 citations into it; #2,101 of 2,242 by trust here, #1,999 by citations

Whom Makoto Otsuka trusts overall

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

1. Andrew Barto
2. Paul J. Werbos
3. Bram Bakker
4. Brian Sallans
5. Richard S. Sutton
6. Florian Heiss
7. Geoffrey E. Hinton
8. Yoav Freund
9. Nicolas Le Roux
10. Satinder Singh

Who trusts Makoto Otsuka overall

1. J. Urgen Schmidhuber
2. Decebal Constantin Mocanu
3. Sergey Levine
4. Yoshua Bengio
5. Tuomas Haarnoja
6. Pieter Abbeel
7. Elena Mocanu
8. Quoc V. Le
9. Trevor Darrell
10. Mohit Bansal

Papers from Makoto Otsuka's perspective

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

1. ImageNet classification with deep convolutional neural networks
2. Reinforcement Learning: An Introduction
3. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
4. Gradient-based learning applied to document recognition
5. Long Short-Term Memory
6. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
7. Attention is All you Need (Neural Information Processing Systems)
8. Learning Multiple Layers of Features from Tiny Images
9. ImageNet Large Scale Visual Recognition Challenge
10. ImageNet: A large-scale hierarchical image database

Their papers

• Free-Energy Based Reinforcement Learning for Vision-Based Navigation with High-Dimensional Sensory Inputs (2010) — 10 citations
• Restricted Boltzmann machines modeling human choice (2014) — 33 citations
• Free-energy-based reinforcement learning in a partially observable environment (2010) — 18 citations
• Goal-Oriented Representations of the External World : A Free-Energy-Based Approach (2010)