We study the problem of the non-parametric estimation for the density of the stationary distribution of a stochastic two-dimensional damping Hamiltonian system . From the continuous observation of the sampling path on , we study the rate of estimation for as . We show that kernel based estimators can achieve the rate for some explicit exponent . One finding is that the rate of estimation depends on the smoothness of and is completely different with the rate appearing in the standard i.i.d.\ setting or in the case of two-dimensional non degenerate diffusion processes. Especially, this rate depends also on . Moreover, we obtain a minimax lower bound on the -risk for pointwise estimation, with the same rate , up to terms.
View on arXiv