Shane Legg
Artificial Intelligence · Neural Information Processing Systems · 2007–2021
A researcher in the Science corpus: 25 papers; trusts 601 researchers and is trusted by 647 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 680 citations into it; #1,369 of 36,961 by trust here, #903 by citations
- Reinforcement Learning — 414 citations into it; #159 of 2,250 by trust here, #18 by citations
- Safety, Robustness & Interpretability — 142 citations into it; #900 of 2,259 by trust here, #817 by citations
- Management Science and Operations Research — 132 citations into it; #4,945 of 12,201 by trust here, #176 by citations
- Computer Vision and Pattern Recognition — 120 citations into it
- Control and Systems Engineering — 88 citations into it; #2,465 of 8,519 by trust here, #144 by citations
- Computational Theory and Mathematics — 83 citations into it; #1,399 of 12,489 by trust here, #182 by citations
- Cognitive Neuroscience — 75 citations into it; #1,434 of 11,026 by trust here, #20 by citations
Whom Shane Legg trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Richard S. Sutton
- J. Urgen Schmidhuber
- Andrew Barto
- Marcus Hutter
- José Hernandez-Orallo
- Geoffrey E. Hinton
- Diederik P. Kingma
- Andrew Y. Ng
- Yoshua Bengio
- Alex Graves
Who trusts Shane Legg overall
- Ben Goertzel
- José Hernandez-Orallo
- Tom Everitt
- Marc G. Bellemare
- Nate Soares
- Jan Leike
- Tom Schaul
- Marcus Hutter
- Joel Veness
- Richard Ngo
Papers from Shane Legg's perspective
Ordered by how strongly the researchers Shane Legg 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
- Gradient-based learning applied to document recognition
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
Their papers
- IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures (2018) — 1,890 citations
- Deep Reinforcement Learning from Human Preferences (2017) — 5,646 citations
- Noisy Networks for Exploration (2017) — 1,022 citations
- Massively Parallel Methods for Deep Reinforcement Learning (2015) — 536 citations
- Reward learning from human preferences and demonstrations in Atari (2018) — 490 citations
- DeepMind Lab (2016) — 267 citations
- Scalable agent alignment via reward modeling: a research direction (2018) — 615 citations
- Universal Intelligence: A Definition of Machine Intelligence (2007) — 761 citations
- AI Safety Gridworlds (2017) — 298 citations
- Shaking the foundations: delusions in sequence models for interaction and control (2021) — 75 citations
- Building Machines that Learn and Think for Themselves: Commentary on Lake et al., Behavioral and Brain Sciences, 2017 (2017) — 38 citations
- An Approximation of the Universal Intelligence Measure (2011) — 71 citations
- Reinforcement Learning with a Corrupted Reward Channel (2017) — 130 citations
- Causal Analysis of Agent Behavior for AI Safety (2021) — 8 citations
- Meta-learning of Sequential Strategies (2019) — 120 citations
- Avoiding Side Effects By Considering Future Tasks (2020) — 51 citations
- Measuring and avoiding side effects using relative reachability (2018) — 24 citations
- Penalizing Side Effects using Stepwise Relative Reachability (2018) — 64 citations
- Agent Incentives: A Causal Perspective (2021) — 71 citations
- Learning Human Objectives by Evaluating Hypothetical Behavior (2019) — 83 citations