DQN-cartPole-tensoflow.py 文件源码

def _createModel(self):

        self.input = tf.placeholder('float', shape=[None,self.stateSize])
        x1 = slim.fully_connected(self.input, 64, scope='fc/fc_1')
        x1 = tf.nn.relu(x1)
        self.Qout = slim.fully_connected(x1, self.actionSize)

        self.tdTarget = tf.placeholder(shape=[None, self.actionSize],dtype=tf.float32)
        self.loss = tf.reduce_mean(tf.square(self.tdTarget - self.Qout ) )

        self.trainer = tf.train.RMSPropOptimizer(learning_rate=0.00025)
        self.updateModel = self.trainer.minimize(self.loss)


        tdTargetLogger= tf.summary.scalar('tdTarget', tf.reduce_mean(self.tdTarget))
        lossLogger= tf.summary.scalar('loss', self.loss)
        self.log = tf.summary.merge([tdTargetLogger, lossLogger])