Masatoshi Uehara

Reinforcement Learning · 2016–2021

A researcher in the Science corpus: 10 papers; trusts 212 researchers and is trusted by 38 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 149 citations into it; #412 of 2,242 by trust here, #885 by citations
• Statistics and Probability — 148 citations into it; #3,111 of 12,932 by trust here, #4,371 by citations
• Artificial Intelligence — 139 citations into it; #5,744 of 35,345 by trust here, #8,619 by citations
• Management Science and Operations Research — 74 citations into it; #6,373 of 11,946 by trust here, #6,314 by citations
• Statistical Learning Theory — 49 citations into it
• Computer Networks and Communications — 26 citations into it; #5,336 of 9,886 by trust here, #6,498 by citations
• Causal Inference & Discovery — 25 citations into it
• Optimization & Training — 23 citations into it; #1,456 of 2,601 by trust here, #1,661 by citations

Whom Masatoshi Uehara trusts overall

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

1. Nathan Kallus
2. Richard S. Sutton
3. Nan Jiang
4. James M. Robins
5. Lihong Li
6. Alex Krizhevsky
7. Sham M. Kakade
8. Anastasios A. Tsiatis
9. Jinyong Hahn
10. Andrew Barto

Who trusts Masatoshi Uehara overall

1. Nathan Kallus
2. Ziyang Tang
3. Nan Jiang
4. Ofir Nachum
5. Balaji Lakshminarayanan
6. Cameron Voloshin
7. Sergey Levine
8. Shangtong Zhang
9. Jiawei Huang
10. Ferenc Huszár

Papers from Masatoshi Uehara's perspective

Ordered by how strongly the researchers Masatoshi Uehara 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. Gradient-based learning applied to document recognition
5. Long Short-Term Memory
6. Attention is All you Need (Neural Information Processing Systems)
7. ImageNet: A large-scale hierarchical image database
8. Learning Multiple Layers of Features from Tiny Images
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. GENERATIVE ADVERSARIAL NETS

Their papers

• Generative Adversarial Nets from a Density Ratio Estimation Perspective (2016) — 106 citations
• Minimax Weight and Q-Function Learning for Off-Policy Evaluation (2019) — 204 citations
• Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes (2019) — 212 citations
• Representation Learning for Online and Offline RL in Low-rank MDPs (2021) — 142 citations
• Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning (2019) — 118 citations
• Statistically Efficient Off-Policy Policy Gradients (2020) — 43 citations
• Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiency (2021) — 60 citations
• Efficient Evaluation of Natural Stochastic Policies in Offline Reinforcement Learning (2020) — 11 citations
• Efficiently Breaking the Curse of Horizon: Double Reinforcement Learning in Infinite-Horizon Processes (2019) — 52 citations
• Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning (2019) — 61 citations