T. Stepleton

Artificial Intelligence · 2016–2022

A researcher in the Science corpus: 8 papers; trusts 39 researchers and is trusted by 90 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 266 citations into it; #3,124 of 35,345 by trust here, #2,822 by citations
• Safety, Robustness & Interpretability — 134 citations into it; #2,125 of 2,251 by trust here, #411 by citations
• Reinforcement Learning — 75 citations into it; #348 of 2,242 by trust here, #488 by citations
• Sociology and Political Science — 72 citations into it
• Safety Research — 70 citations into it
• AI Ethics, Fairness & Society — 52 citations into it
• Optimization & Training — 14 citations into it
• Privacy & Security — 13 citations into it

Whom T. Stepleton trusts overall

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

1. Richard S. Sutton
2. Ben J. A. Kröse
3. Satinder Singh
4. Doina Precup
5. Dimitri P. Bertsekas
6. Andrew Barto
7. A. Mahmood
8. Longxin Lin
9. Silvia Chiappa
10. Martin L. Puterman

Who trusts T. Stepleton overall

1. Marc G. Bellemare
2. Sergey Levine
3. Ofir Nachum
4. Shixiang Shane Gu
5. Ruibo Liu
6. R´emi Munos
7. Nicolas Manfred Otto Heess
8. Josh Merel
9. Scott Fujimoto
10. Yoshua Bengio

Papers from T. Stepleton's perspective

Ordered by how strongly the researchers T. Stepleton 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. Gradient-based learning applied to document recognition
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. Attention is All you Need (Neural Information Processing Systems)
6. Reinforcement Learning: An Introduction
7. Long Short-Term Memory
8. Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
9. Learning Multiple Layers of Features from Tiny Images
10. ImageNet: A large-scale hierarchical image database

Their papers

• Safe and Efficient Off-Policy Reinforcement Learning (2016) — 696 citations
• Ethical and social risks of harm from Language Models (2021) — 1,580 citations
• Q(λ) with Off-Policy Corrections (2016) — 105 citations
• Taxonomy of Risks posed by Language Models (2022) — 1,066 citations
• Counterfactual Credit Assignment in Model-Free Reinforcement Learning (2020) — 73 citations
• A General Approach to Fairness with Optimal Transport (2020) — 97 citations
• Wasserstein Fair Classification (2019) — 216 citations
• Q( λ ) with Off-Policy Corrections