Laurent Orseau
Reinforcement Learning · 2011–2020
A researcher in the Science corpus: 12 papers; trusts 73 researchers and is trusted by 23 researchers here, as inferred from the citation graph.
Subfields
- Reinforcement Learning — 137 citations into it; #1,031 of 2,242 by trust here, #1,139 by citations
- Artificial Intelligence — 128 citations into it; #8,793 of 35,345 by trust here, #8,210 by citations
- Safety, Robustness & Interpretability — 49 citations into it; #435 of 2,251 by trust here, #670 by citations
- Management Science and Operations Research — 28 citations into it
- Control and Systems Engineering — 24 citations into it
- Computational Theory and Mathematics — 21 citations into it; #2,175 of 12,182 by trust here, #2,351 by citations
- Cognitive Neuroscience — 16 citations into it
- Alignment & RLHF — 10 citations into it
Whom Laurent Orseau trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Marcus Hutter
- Ray J. Solomonoff
- Richard S. Sutton
- Stephen W. Carden
- Andrew Barto
- Pieter Abbeel
- Satinder Singh
- J. Urgen Schmidhuber
- Ronald J. Williams
- Andrew Y. Ng
Who trusts Laurent Orseau overall
- Tom Everitt
- Jan Leike
- Victoria Krakovna
- Marcus Hutter
- Eric Langlois
- Miljan Martic
- Shane Legg
- Pedro A. Ortega
- Bill Hibbard
- Jan Leike
Papers from Laurent Orseau's perspective
Ordered by how strongly the researchers Laurent Orseau trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Reinforcement Learning: An Introduction
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- AI Safety Gridworlds (2017) — 298 citations
- An investigation of model-free planning (2019) — 130 citations
- Thompson Sampling is Asymptotically Optimal in General Environments (2016) — 40 citations
- Universal Knowledge-Seeking Agents for Stochastic Environments (2013) — 42 citations
- Space-Time Embedded Intelligence (2012) — 61 citations
- Avoiding Side Effects By Considering Future Tasks (2020) — 51 citations
- Asymptotic non-learnability of universal agents with computable horizon functions (2013) — 16 citations
- Penalizing Side Effects using Stepwise Relative Reachability (2018) — 64 citations
- Delusion, Survival, and Intelligent Agents (2011) — 83 citations
- Measuring and avoiding side effects using relative reachability (2018) — 24 citations
- Reinforcement Learning with a Corrupted Reward Channel (2017) — 130 citations
- Safely Interruptible Agents (2016) — 150 citations