6 papers
State Constrained Stochastic Optimal Control for Continuous and Hybrid Dynamical Systems Using DFBSDE
Bolun Dai, Prashanth Krishnamurthy, Andrew Papanicolaou +1
We develop a computationally efficient learning-based forward-backward stochastic differential equations (FBSDE) controller for both continuous and hybrid dynamical (HD) systems su…
Neural Lyapunov Control for Nonlinear Systems with Unstructured Uncertainties
Shiqing Wei, Prashanth Krishnamurthy, Farshad Khorrami
Stabilizing controller design and region of attraction (RoA) estimation are essential in nonlinear control. Moreover, it is challenging to implement a control Lyapunov function (CL…
Data-Efficient Control Barrier Function Refinement
Bolun Dai, Heming Huang, Prashanth Krishnamurthy +1
Control barrier functions (CBFs) have been widely used for synthesizing controllers in safety-critical applications. When used as a safety filter, it provides a simple and computat…
Data-Driven Deep Learning Based Feedback Linearization of Systems with Unknown Dynamics
Raktim Gautam Goswami, Prashanth Krishnamurthy, Farshad Khorrami
A methodology is developed to learn a feedback linearization (i.e., nonlinear change of coordinates and input transformation) using a data-driven approach for a single input contro…
A Deep Neural Network Algorithm for Linear-Quadratic Portfolio Optimization with MGARCH and Small Transaction Costs
Andrew Papanicolaou, Hao Fu, Prashanth Krishnamurthy +1
We analyze a fixed-point algorithm for reinforcement learning (RL) of optimal portfolio mean-variance preferences in the setting of multivariate generalized autoregressive conditio…
ESAFE: Enterprise Security and Forensics at Scale
Bernard McShea, Kevin Wright, Denley Lam +7
Securing enterprise networks presents challenges in terms of both their size and distributed structure. Data required to detect and characterize malicious activities may be diffuse…