| Record Number | 10258 |
| Reference Type | Conference Paper |
| Author(s) | Evangelos A. Theodorou.;Buchli, J.;Schaal, S. |
| Year | 2009 |
| Title | Path integral stochastic optimal control for rigid body dynamics |
| Journal/Conference/Book Title | IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL2009) |
| Keywords | reinforcement learning, optimal control, path integrals, stochastic systems |
Abstract |
Recent advances on path integral stochastic optimal control cite{cit:1},cite{cit:2} provide new insights on the optimal control of nonlinear stochastic systems which are linear in controls, with state independent and time invariant control transition matrix. Under theses assumptions, the Hamilton-Jacobi-Belman equation is formulated and linearized with the use of the logarithmic transformation of the optimal value function. The resulting HJB is a linear second order partial differential equation which is solved to an approximation based on the Feynman- Kac formula cite{cit:4}. In this work we review the theory of path integral control and derive the linearized HJB equation for systems with state dependent control transition matrix. In addition we derive the path integral formulation for the general class of systems with state dimensionality that is higher than the dimensionality of the controls. Furthermore, by a modified inverse dynamics controller, we apply path integral stochastic optimal control over the new control space. Simulations are illustrated and future developments and extensions are discussed.
|
| Notes | clmc |
| URL(s) | http://www-clmc.usc.edu/publications/t/ADPRL2009.pdf
|
| Link to PDF | http://www-clmc.usc.edu/publications//T/ADPRL2009.pdf |
| Place Published | Nashville, Tenesse, March 30-Aprl 2 |
| Short Title | Path integral stochastic optimal control for rigid body dynamics |
