Towards fast and adaptive optimal control policies for robots: A direct policy search approach - Sorbonne Université Access content directly
Conference Papers Year : 2012

Towards fast and adaptive optimal control policies for robots: A direct policy search approach

Abstract

Optimal control methods are generally too expensive to be applied on-line and in real-time to the control of robots. An alternative method consists in tuning a parametrized reactive controller so that it converges to optimal behavior. In this paper we present such a method based on the "direct Policy Search" paradigm to get a cost-efficient control policy for a simulated two degrees-of-freedom planar arm actuated by six muscles. We learn a parametric controller from demonstration using a few near-optimal trajectories. Then we tune the parameters of this controller using two versions of a Cross-Entropy Policy Search method that we compare. Finally, we show that the resulting controller is 20000 times faster than an optimal control method producing the same trajectories.
No file

Dates and versions

hal-00703755 , version 1 (04-06-2012)

Identifiers

  • HAL Id : hal-00703755 , version 1

Cite

Didier Marin, Olivier Sigaud. Towards fast and adaptive optimal control policies for robots: A direct policy search approach. Robotica 2012, 2012, Guimaraes, Portugal. pp.21-26. ⟨hal-00703755⟩
112 View
0 Download

Share

Gmail Facebook X LinkedIn More