action lists in get_action are different

[Junem360]

@titu1994
hello,
when I use your code, there is a difference between random action generating part and predicting action from controller part in get_action function.

def get_action(self, state):
    '''
    Gets a one hot encoded action list, either from random sampling or from
    the Controller RNN

    Args:
        state: a list of one hot encoded states, whose first value is used as initial
            state for the controller RNN

    Returns:
        A one hot encoded action list
    '''
    if np.random.random() < self.exploration:
        print("Generating random action to explore")
        actions = []

        for i in range(self.state_size * self.num_layers):
            state_ = self.state_space[i]
            size = state_['size']

            sample = np.random.choice(size, size=1)
            sample = state_['index_map_'][sample[0]]
            action = self.state_space.embedding_encode(i, sample)
            actions.append(action)
        return actions

    else:
        print("Prediction action from Controller")
        initial_state = self.state_space[0]
        size = initial_state['size']

        if state[0].shape != (1, size):
            state = state[0].reshape((1, size)).astype('int32')
        else:
            state = state[0]

        print("State input to Controller for Action : ", state.flatten())

        with self.policy_session.as_default():
            K.set_session(self.policy_session)

            with tf.name_scope('action_prediction'):
                pred_actions = self.policy_session.run(self.policy_actions, feed_dict={self.state_input: state})

            return pred_actions

the results of random part are the vectors consist of [0, 1+index number, 0, ...]
but the results of prediction part are the vectors consist of [0, 1, 0, ...] which is one hot encoding.

is it your intention? or just a mistake?

waiting for your answer.
Thanks.