def kl(self, other):
a0 = self.logits - U.max(self.logits, axis=-1, keepdims=True)
a1 = other.logits - U.max(other.logits, axis=-1, keepdims=True)
ea0 = tf.exp(a0)
ea1 = tf.exp(a1)
z0 = U.sum(ea0, axis=-1, keepdims=True)
z1 = U.sum(ea1, axis=-1, keepdims=True)
p0 = ea0 / z0
return U.sum(p0 * (a0 - tf.log(z0) - a1 + tf.log(z1)), axis=-1)
def kl(self, other):
assert isinstance(other, DiagGaussianPd)
return U.sum(
other.logstd - self.logstd +
(tf.square(self.std) + tf.square(self.mean - other.mean)) /
(2.0 * tf.square(other.std)) - 0.5,
axis=-1)
def entropy(self):
return U.sum(tf.nn.sigmoid_cross_entropy_with_logits(
logits=self.logits, labels=self.ps),
axis=-1)
def kl(self, other):
return U.sum(tf.nn.sigmoid_cross_entropy_with_logits(
logits=other.logits, labels=self.ps),
axis=-1) - U.sum(tf.nn.sigmoid_cross_entropy_with_logits(
logits=self.logits, labels=self.ps),
axis=-1)
def neglogp(self, x):
return U.sum(tf.nn.sigmoid_cross_entropy_with_logits(
logits=self.logits, labels=tf.to_float(x)),
axis=-1)
def entropy(self):
return U.sum(self.logstd + .5 * np.log(2.0 * np.pi * np.e), axis=-1)
def neglogp(self, x):
return 0.5 * U.sum(tf.square((x - self.mean) / self.std), axis=-1) \
+ 0.5 * np.log(2.0 * np.pi) * tf.to_float(tf.shape(x)[-1]) \
+ U.sum(self.logstd, axis=-1)
def entropy(self):
a0 = self.logits - U.max(self.logits, axis=-1, keepdims=True)
ea0 = tf.exp(a0)
z0 = U.sum(ea0, axis=-1, keepdims=True)
p0 = ea0 / z0
return U.sum(p0 * (tf.log(z0) - a0), axis=-1)