def __init__(self):
self.original_task = SinFunction()
# Add an additional dimension for the system size
X_lower = np.concatenate(
(self.original_task.original_X_lower, np.array([0])))
X_upper = np.concatenate(
(self.original_task.original_X_upper, np.array([1])))
self.is_env = np.zeros([self.original_task.n_dims])
self.is_env = np.concatenate((self.is_env, np.ones([1])))
super(TestTask, self).__init__(X_lower, X_upper)
def setUp(self):
self.task = SinFunction()
kernel = george.kernels.Matern52Kernel(np.ones([self.task.n_dims]) * 0.01,
ndim=self.task.n_dims)
noise_kernel = george.kernels.WhiteKernel(1e-9, ndim=self.task.n_dims)
kernel = 3000 * (kernel + noise_kernel)
prior = default_priors.TophatPrior(-2, 2)
model = GaussianProcess(kernel, prior=prior)
X = init_random_uniform(self.task.X_lower, self.task.X_upper, 3)
Y = self.task.evaluate(X)
model.train(X, Y, do_optimize=False)
self.acquisition_func = InformationGainMC(model,
X_upper=self.task.X_upper,
X_lower=self.task.X_lower)
self.acquisition_func.update(model)
