Scott Niekum

Artificial Intelligence · 2011–2022

A researcher in the Science corpus: 26 papers; trusts 909 researchers and is trusted by 53 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 505 citations into it; #5,238 of 35,345 by trust here, #5,153 by citations
• Reinforcement Learning — 452 citations into it; #605 of 2,242 by trust here, #676 by citations
• Control and Systems Engineering — 177 citations into it; #2,764 of 8,257 by trust here, #779 by citations
• Computer Vision and Pattern Recognition — 174 citations into it; #11,520 of 21,575 by trust here, #8,021 by citations
• Management Science and Operations Research — 92 citations into it
• Optimization & Training — 54 citations into it
• Computational Theory and Mathematics — 53 citations into it; #9,211 of 12,182 by trust here, #3,924 by citations
• Cognitive Neuroscience — 52 citations into it

Whom Scott Niekum trusts overall

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

1. Richard S. Sutton
2. Geoffrey E. Hinton
3. Sergey Levine
4. Diederik P. Kingma
5. Yoshua Bengio
6. Andrew Y. Ng
7. Pieter Abbeel
8. Ilya Sutskever
9. Alex Krizhevsky
10. Ronald J. Williams

Who trusts Scott Niekum overall

1. Daniel S. Brown
2. Oliver Kroemer
3. Sergey Levine
4. Thomas Kipf
5. Jacob Andreas
6. Pierre Sermanet
7. Philip S. Thomas
8. George Dimitri Konidaris
9. Philip Thomas
10. Harm van Seijen

Papers from Scott Niekum's perspective

Ordered by how strongly the researchers Scott Niekum 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. Long Short-Term Memory
5. Attention is All you Need (Neural Information Processing Systems)
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. GENERATIVE ADVERSARIAL NETS
10. Learning Multiple Layers of Features from Tiny Images

Their papers

• Using Natural Language for Reward Shaping in Reinforcement Learning (2019) — 215 citations
• Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations (2019) — 425 citations
• Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation? (2022) — 102 citations
• Learning grounded finite-state representations from unstructured demonstrations (2015) — 228 citations
• Incremental Semantically Grounded Learning from Demonstration (2013) — 135 citations
• A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms (2019) — 509 citations
• Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluation (2016) — 95 citations
• Active Reward Learning from Critiques (2018) — 80 citations
• Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences (2020) — 116 citations
• Risk-Aware Active Inverse Reinforcement Learning (2018) — 63 citations
• Safe Reinforcement Learning via Shielding (2017) — 968 citations
• Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications (2018) — 85 citations
• Bayesian Robust Optimization for Imitation Learning (2020) — 43 citations
• Importance Sampling Policy Evaluation with an Estimated Behavior Policy (2018) — 73 citations
• Universal Off-Policy Evaluation (2021) — 61 citations
• High Confidence Off-Policy Evaluation with Models (2016) — 5 citations
• You Only Evaluate Once: a Simple Baseline Algorithm for Offline RL (2021) — 8 citations
• The EMPATHIC Framework for Task Learning from Implicit Human Feedback (2020) — 81 citations
• PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards (2020) — 61 citations
• Efficiently Guiding Imitation Learning Algorithms with Human Gaze (2020) — 19 citations