Coder Social home page Coder Social logo

为什么6*6*4train了一天还是0win10loss呢,而且还是乱下棋。。。是不是要修改什么? about alphazero_gomoku HOT 10 CLOSED

junxiaosong avatar junxiaosong commented on May 30, 2024
为什么6*6*4train了一天还是0win10loss呢,而且还是乱下棋。。。是不是要修改什么?

from alphazero_gomoku.

Comments (10)

huyp182 avatar huyp182 commented on May 30, 2024

而且我生成的model是816KB,不是给的408KB的model。。。

from alphazero_gomoku.

junxiaosong avatar junxiaosong commented on May 30, 2024

train了一天大概到多少个iter了?每一步输出的entropy和explained variance大概是个什么情况?按理不用改什么,如果确实不收敛可以试着把learning rate或者kl_target改小一点,会稳定一些

from alphazero_gomoku.

huyp182 avatar huyp182 commented on May 30, 2024

在云服务器上跑,目前到900了,没显示entropy和explained variance。。。
1

from alphazero_gomoku.

junxiaosong avatar junxiaosong commented on May 30, 2024

看你这个输出感觉就没训练。。。而且664下的话个人电脑上1000iter也不用半天,感觉云服务器的环境有点问题吧

from alphazero_gomoku.

huyp182 avatar huyp182 commented on May 30, 2024

我在个人电脑上训练了一天也是这样,才弄到云服务器上去了。。。就是运行的train.py啊。。。不知道为什么生成的model大小和你给的model大小不一样?

from alphazero_gomoku.

junxiaosong avatar junxiaosong commented on May 30, 2024

是最近clone的代码?你可以看下train.py里本来会print出来的信息,然后看看为啥你跑的时候没有输出,没准能发现原因

from alphazero_gomoku.

huyp182 avatar huyp182 commented on May 30, 2024

知道原因了,因为len(data_buffer)=0, batch_size=512,, len(data_buffer)<batch_size,所以不执行policy_update()。
if len(self.data_buffer) > int(self.batch_size):
loss, entropy = self.policy_update()
不知道怎么解决呢?
祝新年快乐!

from alphazero_gomoku.

junxiaosong avatar junxiaosong commented on May 30, 2024

data_buffer里存的是self-play的数据,现在一直为空的话你得看下为啥数据没存进去。如果代码没改过的话,我感觉可能还是python环境的问题

from alphazero_gomoku.

huyp182 avatar huyp182 commented on May 30, 2024

嗯,已解决,不知道将棋盘改为15*15可行吗?

from alphazero_gomoku.

junxiaosong avatar junxiaosong commented on May 30, 2024

理论上可行,但15*15的话对算力要求很高,如果只是在个人电脑上跑的话估计跑不出有意义的结果,太慢了

from alphazero_gomoku.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.