Andrew Aldrich

Reinforcement Learning · 2015–2017

A researcher in the Science corpus: 2 papers; trusts 3 researchers and is trusted by 21 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 8 citations into it

Whom Andrew Aldrich trusts overall

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

1. E. Todorov
2. Nathan Michael

Who trusts Andrew Aldrich overall

1. Yilun Du
2. Arthur Argenson
3. Grady Williams
4. Anusha Nagabandi
5. Igor Mordatch
6. Nicklas Hansen
7. Gabriel Dulac-Arnold
8. Ignasi Clavera
9. Sergey Levine
10. Kevin Lu

Papers from Andrew Aldrich's perspective

Ordered by how strongly the researchers Andrew Aldrich trusts endorse each paper. Same corpus, a different order for every researcher.

1. Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics
2. A generalized iterative LQG method for locally-optimal feedback control of constrained nonlinear stochastic systems
3. Synthesis and stabilization of complex behaviors through online trajectory optimization
4. Differential dynamic programming
5. The GRASP Multiple Micro-UAV Testbed (IEEE robotics & automation magazine)
6. Probabilistic Differential Dynamic Programming
7. LQG-MP: Optimized path planning for robots with motion uncertainty and imperfect state information
8. Stochastic Differential Equations And Applications
9. ImageNet classification with deep convolutional neural networks
10. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)

Their papers

• Model Predictive Path Integral Control: From Theory to Parallel Computation (2017) — 510 citations
• Model Predictive Path Integral Control using Covariance Variable Importance Sampling (2015) — 222 citations