Loading [MathJax]/extensions/TeX/mhchem.js
High-order local dynamic programming | IEEE Conference Publication | IEEE Xplore

High-order local dynamic programming


Abstract:

We describe a new local dynamic programming algorithm for solving stochastic continuous Optimal Control problems. We use cubature integration to both propagate the state ...Show More

Abstract:

We describe a new local dynamic programming algorithm for solving stochastic continuous Optimal Control problems. We use cubature integration to both propagate the state distribution and perform the Bellman backup. The algorithm can approximate the local policy and cost-to-go with arbitrary function bases. We compare the classic quadratic cost-to-go/linear-feedback controller to a cubic cost-to-go/quadratic policy controller on a 10-dimensional simulated swimming robot, and find that the higher order approximation yields a more general policy with a larger basin of attraction.
Date of Conference: 11-15 April 2011
Date Added to IEEE Xplore: 28 July 2011
ISBN Information:

ISSN Information:

Conference Location: Paris, France

References

References is not available for this document.