Riku Arakawa

Reinforcement Learning · 2018–2023

A researcher in the Science corpus: 3 papers; trusts 5 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 22 citations into it
• Artificial Intelligence — 15 citations into it

Whom Riku Arakawa trusts overall

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

1. Longxin Lin
2. W. B. Knox
3. Richard S. Sutton
4. Andrew Y. Ng
5. Christopher J. C. H. Watkins
6. Peter Stone
7. Garrett Warnell
8. Peter S. Dayan
9. Geoffrey E. Hinton
10. Sergey Levine

Who trusts Riku Arakawa overall

1. Lin Guan
2. Ruohan Zhang

Papers from Riku Arakawa's perspective

Ordered by how strongly the researchers Riku Arakawa 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. Reinforcement Learning: An Introduction
8. ImageNet: A large-scale hierarchical image database
9. Learning Multiple Layers of Features from Tiny Images
10. GENERATIVE ADVERSARIAL NETS

Their papers

• DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback (2018) — 92 citations
• Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2023) — 266 citations
• Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations