Stochastic Optimal Control via Measure Relaxations
By: Etienne Buehrle, Christoph Stiller
Potential Business Impact:
Makes smart decisions faster for tricky problems.
The optimal control problem of stochastic systems is commonly solved via robust or scenario-based optimization methods, which are both challenging to scale to long optimization horizons. We cast the optimal control problem of a stochastic system as a convex optimization problem over occupation measures. We demonstrate our method on a set of synthetic and real-world scenarios, learning cost functions from data via Christoffel polynomials. The code for our experiments is available at https://github.com/ebuehrle/dpoc.
Similar Papers
A Calculus of Variations Approach to Stochastic Control
Optimization and Control
Helps make the best money choices for the future.
Deep Learning for Continuous-time Stochastic Control with Jumps
Machine Learning (CS)
Teaches computers to make smart choices automatically.
Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference
Machine Learning (CS)
Guides computers to learn new skills faster.