来自 pixle 的 pong 与 CNN 和策略梯度

Question

我在这一点上卡住了，我已经阅读了 kapathy 博客的“pong from pixel”，我想通过集成 CNN 模型来改进这一点，然后我从 GG 得到了这个导师。

**链接在这里：

https://github.com/yshvrdhn/Pong-Agent-Using-Policy-Gradients/blob/master/pong_keras.py

但我无法运行并且不知道此行的用法： model= learning_model() ，请有人可以帮助我？？？

***我在编译这些代码后得到的错误：

Traceback (most recent call last):
File "C:\Users\thinh dang\Desktop\pong\kerasDemo.py", line 3, in <module>
from keras.models import Sequential
File "C:\Python27\lib\site-packages\keras\__init__.py", line 3, in <module>
from . import utils
File "C:\Python27\lib\site-packages\keras\utils\__init__.py", line 6, in <module>
from . import conv_utils
File "C:\Python27\lib\site-packages\keras\utils\conv_utils.py", line 9, in <module>
from .. import backend as K
File "C:\Python27\lib\site-packages\keras\backend\__init__.py", line 84, in <module>
from .theano_backend import *
File "C:\Python27\lib\site-packages\keras\backend\theano_backend.py", line 7, in <module>
import theano
File "C:\Python27\lib\site-packages\theano\__init__.py", line 110, in <module>
from theano.compile import (
File "C:\Python27\lib\site-packages\theano\compile\__init__.py", line 12, in <module>
from theano.compile.mode import *
File "C:\Python27\lib\site-packages\theano\compile\mode.py", line 11, in <module>
import theano.gof.vm
File "C:\Python27\lib\site-packages\theano\gof\vm.py", line 674, in <module>
from . import lazylinker_c
File "C:\Python27\lib\site-packages\theano\gof\lazylinker_c.py", line 140, in <module>
preargs=args)
File "C:\Python27\lib\site-packages\theano\gof\cmodule.py", line 2388, in compile_str
(status, compile_stderr.replace('\n', '. ')))
Exception: Compilation failed (return status=1): The system cannot find the path specified.

Answer 1

我建议使用 Anaconda。

Answer 2

您似乎没有安装theano。你可以这样做：

pip install theano

作为附带建议，我还推荐使用虚拟环境，这样可以更轻松地隔离您的项目。