GeneZC
GeneZC
我之前训练的时候遇到过类似的情况，有以下解决的方法： 1. 放弃已有的模型，重新训练； 2. 增加模拟的数量（这其实是为了让蒙特卡洛树看到自己输了）； 3. 继续训练下去
'cause parent node and current node belong to different player, and value assigned to each node is according to the player
Looking forward to the open sourced code.
@LeenasTirth Not yet. @liutongyang
使用context_len或text_len影响不大，都达到了正规化的效果。
Thanks for the reply! I actually expect the numbers on sparsities like 70%, 80%, etc.
Many thanks! I would appreciate the results, if available, on other datasets in Table 2 as well. Otherwise, I will have to produce the results by running the code.
那145和160行也得改
为什么作者一开始要那样写呢？
How about setting max len to 83 instead ?