Learning Cost-Efficient Control Policies with XCSF: Generalization Capabilities and Further Improvement

Abstract : In this paper we present a method based on the "learning from demonstration" paradigm to get a cost-efficient control policy in a continuous state and action space. The controlled plant is a two degrees-of-freedom planar arm actuated by six muscles. We learn a parametric control policy with xcsf from a few near-optimal trajectories, and we study its capability to generalize over the whole reachable space. Furthermore, we show that an additional Cross-Entropy Policy Search method can improve the global performance of the parametric controller.
Document type :
Conference papers
Complete list of metadatas

https://hal.sorbonne-universite.fr/hal-00703760
Contributor : Didier Marin <>
Submitted on : Monday, June 4, 2012 - 12:22:48 PM
Last modification on : Thursday, March 21, 2019 - 1:06:15 PM

Identifiers

  • HAL Id : hal-00703760, version 1

Citation

Didier Marin, Jérémie Decock, Lionel Rigoux, Olivier Sigaud. Learning Cost-Efficient Control Policies with XCSF: Generalization Capabilities and Further Improvement. GECCO 2011, 2011, Dublin, Ireland. pp.1235-1242. ⟨hal-00703760⟩

Share

Metrics

Record views

280