[强化学习马里奥 MarioRL]--环境安装 1

这个真不会啊

已于 2024-07-12 15:26:08 修改

阅读量137

点赞数 1

分类专栏：强化学习文章标签： python 深度学习

于 2024-07-12 13:35:59 首次发布

本文链接：https://blog.csdn.net/qhr_1012/article/details/140376819

版权

强化学习专栏收录该内容

6 篇文章 0 订阅

订阅专栏

建议使用conda环境进行包管理 torch gym包默认安装好了

官方推荐安装：

git上SetUp直接干

但是我改了下路径

environment.yml

prefix: /opt/anaconda3/envs/mario
改成
prefix: /home/qhr/anaconda3/envs/mario

但是报错：

还是自己手动装吧

conda create -n mario python=3.8

(mario) ➜  MadMario-master pip3 install gym==0.17.2 -i https://pypi.doubanio.com/simple/ --target=/home/qhr/anaconda3/envs/mario/lib/python3.8/site-packages

(mario) ➜  MadMario-master pip3 install gym_super_mario_bros==7.3.0 -i https://pypi.doubanio.com/simple/ --target=/home/qhr/anaconda3/envs/mario/lib/python3.8/site-packages

(mario) ➜  MadMario-master pip3 install matplotlib -i https://pypi.doubanio.com/simple/ --target=/home/qhr/anaconda3/envs/mario/lib/python3.8/site-packages

(mario) ➜  MadMario-master pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118 --target=/home/qhr/anaconda3/envs/mario/lib/python3.8/site-packages            

(mario) ➜  MadMario-master pip3 install scikit-image -i https://pypi.doubanio.com/simple/ --target=/home/qhr/anaconda3/envs/mario/lib/python3.8/site-packages

(mario) ➜  MadMario-master pip3 install opencv-python==4.2.0.34 -i https://pypi.doubanio.com/simple/ --target=/home/qhr/anaconda3/envs/mario/lib/python3.8/site-packages

有个报错没查出来啥问题但是能跑了后面再说

安装的pip3环境如下：requirements.txt

requirements.txt


cloudpickle==1.3.0
contourpy==1.1.1
cycler==0.12.1
filelock==3.13.1
fonttools==4.53.1
fsspec==2024.2.0
future==1.0.0
gym==0.17.2
gym-notices==0.0.8
gym-super-mario-bros==7.3.0
imageio==2.34.2
importlib_metadata==8.0.0
importlib_resources==6.4.0
Jinja2==3.1.3
kiwisolver==1.4.5
lazy_loader==0.4
MarkupSafe==2.1.5
matplotlib==3.7.5
mpmath==1.3.0
nes_py==8.2.1
networkx==3.0
numpy==1.18.4
nvidia-cublas-cu11==11.11.3.6
nvidia-cuda-cupti-cu11==11.8.87
nvidia-cuda-nvrtc-cu11==11.8.89
nvidia-cuda-runtime-cu11==11.8.89
nvidia-cudnn-cu11==8.7.0.84
nvidia-cufft-cu11==10.9.0.58
nvidia-curand-cu11==10.3.0.86
nvidia-cusolver-cu11==11.4.1.48
nvidia-cusparse-cu11==11.7.5.86
nvidia-nccl-cu11==2.20.5
nvidia-nvtx-cu11==11.8.86
opencv-python==4.2.0.34
packaging==24.1
pillow==10.2.0
pyglet==1.5.0
pyparsing==3.1.2
python-dateutil==2.9.0.post0
PyWavelets==1.4.1
scikit-image==0.21.0
scipy==1.10.1
six==1.16.0
sympy==1.12
tifffile==2023.7.10
torch==2.3.1+cu118
torchaudio==2.3.1+cu118
torchvision==0.18.1+cu118
tqdm==4.66.4
triton==2.3.1
typing_extensions==4.9.0
zipp==3.19.2