Comments (10)
而且我生成的model是816KB,不是给的408KB的model。。。
from alphazero_gomoku.
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.
在云服务器上跑,目前到900了,没显示entropy和explained variance。。。
from alphazero_gomoku.
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.
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.
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.
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.
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.
嗯,已解决,不知道将棋盘改为15*15可行吗?
from alphazero_gomoku.
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)
- Potential error HOT 1
- 关于训练过程的疑问
- Differences between model amd model2
- alpha zero是如何避免在不可行的位置落子的 HOT 2
- 修改了游戏规则后训练中的问题
- 关于训练中断
- 用Pytorch训练保存模型,在human_play中加载模型报错 HOT 2
- 请问这个网络是多少*多少的大小 HOT 1
- 非常想请教一个问题,希望大佬回复 HOT 4
- roll out in mcts_pure
- python GUI + 代码分析
- 请问如何使用自己训练的权重
- 为什么要在'play_data'中反转输入特征?
- 各位训练了多久,能下赢自己?
- 关于pytorch训练无法收敛的问题 HOT 6
- 算法并非自己对战
- Keras implementation is not RL
- Asymmetrical game board can't be trainned 棋盘宽和长不等时,如何训练?
- 模型参数形状与从检查点文件中加载的参数形状不匹配 HOT 1
- 怎么保存固定迭代次数的模型或者怎么看Elo等级分
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from alphazero_gomoku.