def propensity(self, x, action):
xp = cuda.get_array_module(x)
""": type: numpy"""
# Compute independent thompson sample distributions
z_means = xp.zeros((x.shape[0], self.k))
z_std = xp.zeros((x.shape[0], self.k))
for a in range(self.k):
m, s = self.regressors[a].thompson_distribution(x)
z_means[:, a] = m.data
z_std[:, a] = s.data
# Compute the argmax probability
m_i, m_j = _tiles(z_means)
s_i, s_j = _tiles(z_std)
c_m = _cut_diagonals(m_i - m_j).data
c_s = _cut_diagonals(s_i + s_j).data
opts = factorial(self.k - 1)
res = xp.prod(0.5 * (1 + F.erf(c_m / (xp.sqrt(2) * c_s)).data), axis=2)
a = F.reshape(action, (action.shape[0], 1))
res = select_items_per_row(as_variable(res), a)
return F.reshape(res, action.shape)
def _ndtr(a):
"""CDF of the standard normal distribution.
See https://github.com/scipy/scipy/blob/master/scipy/special/cephes/ndtr.c
"""
if not isinstance(a, chainer.Variable):
a = chainer.Variable(a)
x = a * NPY_SQRT1_2
z = abs(x)
half_erfc_z = 0.5 * F.erfc(z)
return F.where(z.data < NPY_SQRT1_2, 0.5 + 0.5 * F.erf(x),
F.where(x.data > 0, 1.0 - half_erfc_z, half_erfc_z))
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + F.erf(input_tensor / 2.0 ** 0.5))
return input_tensor * cdf
def gelu(input_tensor):
"""Gaussian Error Linear Unit.
This is a smoother version of the RELU.
Original paper: https://arxiv.org/abs/1606.08415
Args:
input_tensor: float Tensor to perform activation.
Returns:
`input_tensor` with the GELU activation applied.
"""
cdf = 0.5 * (1.0 + F.erf(input_tensor / 2.0 ** 0.5))
return input_tensor * cdf