odu.py 文件源码

def get_greedy(self, v):
        """
        Compute optimal actions taking v as the value function.

        Parameters
        ----------
        v : array_like(float, ndim=1, length=len(?_grid))
            An approximate value function represented as a
            one-dimensional array.

        Returns
        -------
        policy : array_like(float, ndim=1, length=len(?_grid))
            The decision to accept or reject an offer where 1 indicates
            accept and 0 indicates reject

        """
        # == Simplify names == #
        f, g, ?, c, q = self.f, self.g, self.?, self.c, self.q

        vf = LinearNDInterpolator(self.grid_points, v)
        N = len(v)
        policy = np.zeros(N, dtype=int)

        for i in range(N):
            w, ? = self.grid_points[i, :]
            v1 = w / (1 - ?)
            integrand = lambda m: vf(m, q(m, ?)) * (? * f(m) +
                                                     (1 - ?) * g(m))
            integral, error = fixed_quad(integrand, 0, self.w_max)
            v2 = c + ? * integral
            policy[i] = v1 > v2  # Evaluates to 1 or 0

        return policy