def create_nn(self, features, name=None):
if name is None:
name = self.critic_name
with tf.variable_scope(name + '_fc_1'):
fc1 = layer(features, 64)
with tf.variable_scope(name + '_fc_2'):
fc2 = layer(fc1, 64)
with tf.variable_scope(name + '_fc_3'):
fc3 = layer(fc2, 64)
with tf.variable_scope(name + '_fc_4'):
fc4 = layer(fc3, 1, is_output=True)
return fc4
def create_nn(self, features, name=None):
if name is None:
name = self.actor_name
with tf.variable_scope(name + '_fc_1'):
fc1 = layer(features, 64)
with tf.variable_scope(name + '_fc_2'):
fc2 = layer(fc1, 64)
with tf.variable_scope(name + '_fc_3'):
fc3 = layer(fc2, 64)
with tf.variable_scope(name + '_fc_4'):
fc4 = layer(fc3, self.action_space_size, is_output=True)
output = tf.tanh(fc4) * self.action_space_bounds + self.action_offset
return output
def create_nn(self, features, name=None):
if name is None:
name = self.critic_name
with tf.variable_scope(name + '_fc_1'):
fc1 = layer(features, 64)
with tf.variable_scope(name + '_fc_2'):
fc2 = layer(fc1, 64)
with tf.variable_scope(name + '_fc_3'):
fc3 = layer(fc2, 64)
with tf.variable_scope(name + '_fc_4'):
fc4 = layer(fc3, 1, is_output=True)
# A q_offset is used to give the critic function an optimistic initialization near 0
output = tf.sigmoid(fc4 + self.q_offset) * self.q_limit
return output