umenberger

robust-deepc

Code to reproduce examples in 'Closed-loop data-enabled predictive control' submitted to CDC 2020

robust-exploration

Code to reproduce examples in NeurIPS submission: Robust exploration in linear quadratic reinforcement learning.

hmc_input_design

informativity-regularization

Regularization to ensure convergence of policy gradient for output estimation.

umenberger.github.io

NonlinearID

Nonlinear System Identification (aka Learning Dynamical Systems) with guaranteed stability/contraction

b1-coding-practical-mt24

Coding practical task for the B1 Scientific Coding course at Oxford (MT24)

umenberger/umenberger.github.io

umenberger/informativity-regularization

Regularization to ensure convergence of policy gradient for output estimation.

umenberger/robust-deepc

Code to reproduce examples in 'Closed-loop data-enabled predictive control' submitted to CDC 2020

umenberger/robust-exploration

Code to reproduce examples in NeurIPS submission: Robust exploration in linear quadratic reinforcement learning.

umenberger/hmc_input_design