问题：
self.q_eval4next： （100,2）
ix=【0,1,0,1---0，1】（100,1）
我想取q_eval4next[:,idx]
1 #use_doubleQ 切片用！！！！ 2 self.range_index = tf.placeholder(tf.int32,[None,],name='range_index') 3 4 if self.use_doubleQ: 5 6 f = tf.map_fn(lambda x: x, self.range_index) # or perhaps something more useful than identity 7 ix = tf.to_int32(tf.expand_dims(tf.argmax(self.q_eval4next,axis=1),-1)) 8 tmp=tf.to_int32(tf.expand_dims(f,-1)) 9 index_a = tf.concat([tmp,ix,],axis=1) 10 maxq = tf.gather_nd(self.q_next,index_a)
https://www.programcreek.com/python/example/90420/tensorflow.map_fn
https://stackoverflow.com/questions/34987509/tensorflow-max-of-a-tensor-along-an-axis
https://zhuanlan.zhihu.com/p/39295071
https://zhuanlan.zhihu.com/p/45673869