学会使用强化学习框架Acme(4)

建议先简单看下

学会使用强化学习框架Acme(3)_wo_squirrel的博客-CSDN博客建议粗略看下之前的 学会使用强化学习框架Acme(1) (2)进到acme的子目录examplesacme/examples at master · deepmind/acme · GitHub下载好acme在github上的所有文件。进入下载好的目录并用jupyter打开quickstart.ipynb(acme) jw@Z8:~/acme-master/examples$ jupyter-notebook...https://blog.csdn.net/wo_squirrel/article/details/124289593

还是同一个代码块，但是出现了不同的错误：

代码：

import IPython

from acme import environment_loop
from acme import specs
from acme import wrappers
from acme.agents.tf import d4pg
from acme.tf import networks
from acme.tf import utils as tf2_utils
from acme.utils import loggers
import numpy as np
import sonnet as snt

# Import the selected environment lib
if environment_library == 'dm_control':
  from dm_control import suite
elif environment_library == 'gym':
  import gym

# Imports required for visualization
import pyvirtualdisplay
import imageio
import base64

# Set up a virtual display for rendering.
display = pyvirtualdisplay.Display(visible=0, size=(1400, 900)).start()

错误：

2022-05-08 10:12:23.953387: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: :/home/jw/anaconda3/envs/acme/lib
2022-05-08 10:12:23.953405: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
/home/jw/anaconda3/envs/acme/lib/python3.9/site-packages/flatbuffers/compat.py:19: DeprecationWarning: the imp module is deprecated in favour of importlib; see the module's documentation for alternative uses
  import imp
/home/jw/anaconda3/envs/acme/lib/python3.9/site-packages/keras_preprocessing/image/utils.py:23: DeprecationWarning: NEAREST is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.NEAREST or Dither.NONE instead.
  'nearest': pil_image.NEAREST,
/home/jw/anaconda3/envs/acme/lib/python3.9/site-packages/keras_preprocessing/image/utils.py:24: DeprecationWarning: BILINEAR is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BILINEAR instead.
  'bilinear': pil_image.BILINEAR,
/home/jw/anaconda3/envs/acme/lib/python3.9/site-packages/keras_preprocessing/image/utils.py:25: DeprecationWarning: BICUBIC is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BICUBIC instead.
  'bicubic': pil_image.BICUBIC,
/home/jw/anaconda3/envs/acme/lib/python3.9/site-packages/keras_preprocessing/image/utils.py:28: DeprecationWarning: HAMMING is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.HAMMING instead.
  if hasattr(pil_image, 'HAMMING'):
/home/jw/anaconda3/envs/acme/lib/python3.9/site-packages/keras_preprocessing/image/utils.py:30: DeprecationWarning: BOX is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BOX instead.
  if hasattr(pil_image, 'BOX'):
/home/jw/anaconda3/envs/acme/lib/python3.9/site-packages/keras_preprocessing/image/utils.py:33: DeprecationWarning: LANCZOS is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.LANCZOS instead.
  if hasattr(pil_image, 'LANCZOS'):
/home/jw/anaconda3/envs/acme/lib/python3.9/site-packages/reverb/platform/default/ensure_tf_install.py:53: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
  if (distutils.version.LooseVersion(version) <
/home/jw/anaconda3/envs/acme/lib/python3.9/site-packages/sonnet/src/types.py:34: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  BoolLike = Union[bool, np.bool, TensorLike]
/home/jw/anaconda3/envs/acme/lib/python3.9/site-packages/tensorflow_probability/python/__init__.py:57: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
  if (distutils.version.LooseVersion(tf.__version__) <

这是因为没有安装cudatoolkit。

---

查看GPU使用情况（可以看到驱动版本和CUDA版本）：

nvidia-smi

---

跟着这篇文章安装

Ubuntu20.04安装tensorflow2.8.0+CUDA11.4_图南i的博客-CSDN博客

文章中的1，2步我之前都做好了，第三步是跟着cuda官网的两行代码安装的

官网：CUDA Toolkit 11.4 Downloads | NVIDIA Developer

代码：

$ wget https://developer.download.nvidia.com/compute/cuda/11.4.0/local_installers/cuda_11.4.0_470.42.01_linux.run
$ sudo sh cuda_11.4.0_470.42.01_linux.run

因为我的显卡驱动已经装好了（510），所以没有选择安装驱动。

然后就是添加环境变量，跟着文章一起做就行了，但是在打开/etc/ld.so.conf的时候要这样做

sudo gedit /etc/ld.so.conf #不加sudo，文件只读

然后就是跟着文章一起做，最后测试是否安装好了的时候，要这样做

>>> tf.__version__
'2.8.0'
>>> tf.config.list_physical_devices('GPU')
[PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')]

安装成功。