ObstacleRL.py 文件源码

def __init__(self, lr, s_size, a_size):

        self.state_in = tf.placeholder(shape=[1], dtype=tf.int32)
        state_in_OH = slim.one_hot_encoding(self.state_in, s_size)

        output = slim.fully_connected(state_in_OH, 
                                        a_size, 
                                        biases_initializer=None, 
                                        activation_fn=tf.nn.sigmoid,
                                        weights_initializer=tf.ones_initializer())
        self.output = tf.reshape(output, [-1])

        self.chosen_action = tf.argmax(self.output, 0)
        self.reward_holder = tf.placeholder(shape=[1], dtype=tf.float32)
        self.action_holder = tf.placeholder(shape=[1], dtype=tf.int32)

        self.responsible_weight = tf.slice(self.output, self.action_holder, [1])

        self.loss = -(tf.log(self.responsible_weight) * self.reward_holder)
        optimizer = tf.train.GradientDescentOptimizer(learning_rate=lr)
        self.update = optimizer.minimize(self.loss)