Header logo is

An Iterative Path Integral Stochastic Optimal Control Approach for Learning Robotic Tasks

2011

Conference Paper

am


Recent work on path integral stochastic optimal control theory Theodorou et al. (2010a); Theodorou (2011) has shown promising results in planning and control of nonlinear systems in high dimensional state spaces. The path integral control framework relies on the transformation of the nonlinear Hamilton Jacobi Bellman (HJB) partial differential equation (PDE) into a linear PDE and the approximation of its solution via the use of the Feynman Kac lemma. In this work, we are reviewing the generalized version of path integral stochastic optimal control formalism Theodorou et al. (2010a), used for optimal control and planing of stochastic dynamical systems with state dependent control and diffusion matrices. Moreover we present the iterative path integral control approach, the so called Policy Improvement with Path Integrals or (PI2 ) which is capable of scaling in high dimensional robotic control problems. Furthermore we present a convergence analysis of the proposed algorithm and we apply the proposed framework to a variety of robotic tasks. Finally with the goal to perform locomotion the iterative path integral control is applied for learning nonlinear limit cycle attractors with adjustable land scape.

Author(s): E. Theodorou and F. Stulp and J. Buchli and S. Schaal
Book Title: Proceedings of the 18th World Congress of the International Federation of Automatic Control
Year: 2011

Department(s): Autonomous Motion
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Cross Ref: p10394
Note: clmc

Links: PDF

BibTex

@inproceedings{EvangelosIFAC11,
  title = {An Iterative Path Integral Stochastic Optimal Control Approach for Learning  Robotic Tasks  },
  author = {Theodorou, E. and Stulp, F. and Buchli, J. and Schaal, S.},
  booktitle = {Proceedings of the 18th World Congress of the International Federation of Automatic Control},
  year = {2011},
  note = {clmc},
  crossref = {p10394}
}