| Title | Stochastic Optimal Control via Hilbert Space Embeddings of Distributions |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Thorpe, Adam J., Oishi, Meeko M. K. |
| Conference Name | 2021 60th IEEE Conference on Decision and Control (CDC) |
| Date Published | dec |
| Keywords | Heuristic algorithms, Hilbert space, machine learning, optimal control, pubcrawl, Regulation, resilience, Resiliency, Scalability, Stochastic Computing Security, stochastic systems, target tracking |
| Abstract | Kernel embeddings of distributions have recently gained significant attention in the machine learning community as a data-driven technique for representing probability distributions. Broadly, these techniques enable efficient computation of expectations by representing integral operators as elements in a reproducing kernel Hilbert space. We apply these techniques to the area of stochastic optimal control theory and present a method to compute approximately optimal policies for stochastic systems with arbitrary disturbances. Our approach reduces the optimization problem to a linear program, which can easily be solved via the Lagrangian dual, without resorting to gradient-based optimization algorithms. We focus on discrete- time dynamic programming, and demonstrate our proposed approach on a linear regulation problem, and on a nonlinear target tracking problem. This approach is broadly applicable to a wide variety of optimal control problems, and provides a means of working with stochastic systems in a data-driven setting. |
| DOI | 10.1109/CDC45484.2021.9682801 |
| Citation Key | thorpe_stochastic_2021 |
Stochastic Optimal Control via Hilbert Space Embeddings of Distributions