mlsh_code/policy_network.py [48:59]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def act(self, stochastic, ob):
        ac1, vpred1 =  self._act(stochastic, ob[None])
        return ac1[0], vpred1[0]
    def get_variables(self):
        return tf.get_collection(tf.GraphKeys.VARIABLES, self.scope)
    def get_trainable_variables(self):
        return tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, self.scope)
    def reset(self):
        with tf.variable_scope(self.scope, reuse=True):
            varlist = self.get_trainable_variables()
            initializer = tf.variables_initializer(varlist)
            U.get_session().run(initializer)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -