Tom Everitt
Artificial Intelligence · 2016–2021
A researcher in the Science corpus: 15 papers; trusts 272 researchers and is trusted by 23 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 370 citations into it; #9,146 of 35,345 by trust here, #4,682 by citations
- Reinforcement Learning — 283 citations into it; #905 of 2,242 by trust here, #652 by citations
- Safety, Robustness & Interpretability — 178 citations into it; #562 of 2,251 by trust here, #743 by citations
- Computational Theory and Mathematics — 88 citations into it; #11,791 of 12,182 by trust here, #8,294 by citations
- Management Science and Operations Research — 67 citations into it
- Alignment & RLHF — 51 citations into it; #19 of 62 by trust here, #26 by citations
- Philosophy — 41 citations into it
- Control and Systems Engineering — 40 citations into it
Whom Tom Everitt trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Richard S. Sutton
- Laurent Orseau
- Jessica Taylor
- J. Urgen Schmidhuber
- Andrew Y. Ng
- Geoffrey E. Hinton
- Bill Hibbard
- Stuart Armstrong
- Andrew Barto
- Pieter Abbeel
Who trusts Tom Everitt overall
- Jan Leike
- Zachary Kenton
- David Krueger
- Shane Legg
- Iason Gabriel
- Eric Langlois
- Ramana Kumar
- Victoria Krakovna
- Richard Ngo
- Marcus Hutter
Papers from Tom Everitt's perspective
Ordered by how strongly the researchers Tom Everitt trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Learning Multiple Layers of Features from Tiny Images
Their papers
- Alignment of Language Agents (2021) — 227 citations
- Scalable agent alignment via reward modeling: a research direction (2018) — 615 citations
- AI Safety Gridworlds (2017) — 298 citations
- Count-Based Exploration in Feature Space for Reinforcement Learning (2017) — 132 citations
- AGI Safety Literature Review (2018) — 132 citations
- Self-Modification of Policy and Utility Function in Rational Agents (2016) — 36 citations
- How RL Agents Behave When Their Actions Are Modified (2021) — 19 citations
- Modeling AGI Safety Frameworks with Causal Influence Diagrams (2019) — 24 citations
- Agent Incentives: A Causal Perspective (2021) — 71 citations
- Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective (2019) — 156 citations
- The Alignment Problem for Bayesian History-Based Reinforcement Learners∗ (2019)
- Understanding Agent Incentives using Causal Influence Diagrams. Part I: Single Action Settings (2019) — 33 citations
- Towards Safe Artificial General Intelligence (2018) — 24 citations
- Reinforcement Learning with a Corrupted Reward Channel (2017) — 130 citations
- Avoiding Wireheading with Value Reinforcement Learning (2016) — 51 citations