Learning Cost-Efficient Control Policies with XCSF: Generalization Capabilities and Further Improvement
Didier Marin, Jérémie Decock, Lionel Rigoux, Olivier Sigaud · 2011
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 ca-pability to generalize over the whole reachable space. Fur-thermore, we show that an additional Cross-Entropy Policy Search method can improve the global performance of the parametric controller.