42 citations · 87 across the 3 of their papers we have counts for
3 papers
cs.LG2020★ 28 cited
Learning Stability Certificates from Data
Nicholas M. Boffi, Stephen Tu, Nikolai Matni +2
Many existing tools in nonlinear control theory for establishing stability or safety of a dynamical system can be distilled to the construction of a certificate function that guara…
cs.LG2019★ 17 cited
Observational Overfitting in Reinforcement Learning
Xingyou Song, Yiding Jiang, Stephen Tu +2
A major component of overfitting in model-free reinforcement learning (RL) involves the case where the agent may mistakenly correlate reward with certain spurious features from the…
math.OC2019★ 42 cited
Certainty Equivalence is Efficient for Linear Quadratic Control
Horia Mania, Stephen Tu, Benjamin Recht
We study the performance of the certainty equivalent controller on Linear Quadratic (LQ) control problems with unknown transition dynamics. We show that for both the fully and part…