On Learning Discontinuous Human Control Strategies*
Ž . Ž. Ž. Ž.k 1 4 k,minŽ.Ž . k ggb,4000,max k,0, Ž. Ž.k 03 Ž . Ž. Ž. Ž.k 1 4 k,maxŽ.Ž. k bbg, 8000,min k,0, Ž. Ž.k 04 For the experiments in this paper, we collect human driving data across randomly generated roads like the 20 km one shown in the map of Figure 1. The roads are described by a sequence of 1 straight-line ...