请问有没有unity外接python算法进行强化学习训练的课程呢

求教一下老师，我这个是哪的问题，点击play后 没有训练。
2-14 10:25:14 INFO [stats.py:121] RollerBall: Step: 12000. No episode was completed since last summary. Training.
2023-02-14 10:26:00 INFO [stats.py:121] RollerBall: Step: 24000. No episode was completed since last summary. Training.
2023-02-14 10:26:45 INFO [stats.py:121] RollerBall: Step: 36000. No episode was completed since last summary. Training.
2023-02-14 10:27:37 INFO [stats.py:121] RollerBall: Step: 48000. No episode was completed since last summary. Training.
2023-02-14 10:28:28 INFO [stats.py:121] RollerBall: Step: 60000. No episode was completed since last summary. Training.
2023-02-14 10:29:18 INFO [stats.py:121] RollerBall: Step: 72000. No episode was completed since last summary. Training.
2023-02-14 10:30:10 INFO [stats.py:121] RollerBall: Step: 84000. No episode was completed since last summary. Training.

非常好

太强了 希望老师 出更多的Unity的教程

太强了 希望老师 出更多的Unity的教程

输入：mlagents-learn config.yaml 之后不像老师那样小球开始运行，是什么情况呢？ Anaconda Prompt运行结果如下内容

(unity_py_3.6_siki) D:\Test\Unity\Git\Roll_A_Ball\Code\MyRoll_A_Ball\Assets\My\Train>mlagents-learn config.yaml

Version information:
ml-agents: 0.28.0,
ml-agents-envs: 0.28.0,
Communicator API: 1.5.0,
PyTorch: 1.7.0+cpu
Traceback (most recent call last):
File "D:\Software\Anaconda3\Exe\envs\unity_py_3.6_siki\lib\runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "D:\Software\Anaconda3\Exe\envs\unity_py_3.6_siki\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "D:\Software\Anaconda3\Exe\envs\unity_py_3.6_siki\Scripts\mlagents-learn.exe\__main__.py", line 7, in
File "D:\Software\Anaconda3\Exe\envs\unity_py_3.6_siki\lib\site-packages\mlagents\trainers\learn.py", line 260, in main
run_cli(parse_command_line())
File "D:\Software\Anaconda3\Exe\envs\unity_py_3.6_siki\lib\site-packages\mlagents\trainers\learn.py", line 256, in run_cli
run_training(run_seed, options, num_areas)
File "D:\Software\Anaconda3\Exe\envs\unity_py_3.6_siki\lib\site-packages\mlagents\trainers\learn.py", line 75, in run_training
checkpoint_settings.maybe_init_path,
File "D:\Software\Anaconda3\Exe\envs\unity_py_3.6_siki\lib\site-packages\mlagents\trainers\directory_utils.py", line 26, in validate_existing_directories
"Previous data from this run ID was found. "
mlagents.trainers.exception.UnityTrainerException: Previous data from this run ID was found. Either specify a new run ID, use --resume to resume this run, or use the --force parameter to overwrite existing data.

(unity_py_3.6_siki) D:\Test\Unity\Git\Roll_A_Ball\Code\MyRoll_A_Ball\Assets\My\Train>

pip install mlagents之后没有tensorflow，一切输出都正确，唯独最后列表里面没有tensorflow

这是全部的命令行：
(base) C:\Users\Ethan>activate unity

(unity) C:\Users\Ethan>pip install mlagents -i https://pypi.tuna.tsinghua.edu.cn/simple
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Collecting mlagents
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/d5/fd/f69794548cb3ccf7d2d132b3dbeff95222f7d665ec07d19e11e316e37536/mlagents-0.27.0-py3-none-any.whl (160 kB)
Collecting Pillow>=4.2.1
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/ff/fb/506890622e1dcddaa3b215a6cef70d72c4e248feed0045eb52904d1ef80b/Pillow-8.4.0-cp38-cp38-win_amd64.whl (3.2 MB)
|████████████████████████████████| 3.2 MB 1.6 MB/s
Collecting mlagents-envs==0.27.0
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/d1/b4/ed6e5cbcd091324bc8c2f3f23bcba794bd7610a5e6a154b881bce6f9993b/mlagents_envs-0.27.0-py3-none-any.whl (75 kB)
Collecting cattrs<1.7,>=1.1.0
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/06/40/9a3f0e80af334bd808549c0b09fafe44269ddf261933f97723fd9b3f0deb/cattrs-1.6.0-py3-none-any.whl (22 kB)
Collecting attrs>=19.3.0
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/20/a9/ba6f1cd1a1517ff022b35acd6a7e4246371dfab08b8e42b829b6d07913cc/attrs-21.2.0-py2.py3-none-any.whl (53 kB)
Collecting numpy<2.0,>=1.13.3
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/15/3d/70e9393b786c2464cb3060249901ace93b154495c2f2598930d06bb187f6/numpy-1.21.4-cp38-cp38-win_amd64.whl (14.0 MB)
|████████████████████████████████| 14.0 MB 6.4 MB/s
Collecting pyyaml>=3.1.0
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/a8/5b/c4d674846ea4b07ee239fbf6010bcc427c4e4552ba5655b446e36b9a40a7/PyYAML-6.0-cp38-cp38-win_amd64.whl (155 kB)
|████████████████████████████████| 155 kB 2.2 MB/s
Collecting grpcio>=1.11.0
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/62/93/906e58b0c44da703c4e3897ae78f165408153937362ae1faa424caf6505b/grpcio-1.41.1-cp38-cp38-win_amd64.whl (3.2 MB)
|████████████████████████████████| 3.2 MB 2.2 MB/s
Collecting protobuf>=3.6
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/a0/5c/d8bae5c0e15945839a827b36d634bcfde091d8792cbeec76b130d8546aac/protobuf-3.19.1-cp38-cp38-win_amd64.whl (895 kB)
|████████████████████████████████| 895 kB 6.4 MB/s
Collecting tensorboard>=1.15
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/2d/eb/80f75ab480cfbd032442f06ec7c15ef88376c5ef7fd6f6bf2e0e03b47e31/tensorboard-2.7.0-py3-none-any.whl (5.8 MB)
Collecting pypiwin32==223
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/d0/1b/2f292bbd742e369a100c91faa0483172cd91a1a422a6692055ac920946c5/pypiwin32-223-py3-none-any.whl (1.7 kB)
Collecting h5py>=2.9.0
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/d1/52/14d592123eee586ba2bbbcd9288fea74d8dbc8125210cb32e206ff51db5f/h5py-3.5.0-cp38-cp38-win_amd64.whl (2.8 MB)
|████████████████████████████████| 2.8 MB 1.7 MB/s
Collecting cloudpickle
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/07/3c/bf72ebd3e78eb1ef773f4f0650ecdc29c6454aeafe9c08f6da3f227dd2bc/cloudpickle-2.0.0-py3-none-any.whl (25 kB)
Collecting pywin32>=223
Downloading https://pypi.tuna.tsinghua.edu.cn/packages/b1/e6/ddf43219ac2b2145b73bb7dc2163abbf0ea83a6d01ff7284b053eaf531e7/pywin32-302-cp38-cp38-win_amd64.whl (9.3 MB)
|████████████████████████████████| 9.3 MB 2.2 MB/s
Collecting six>=1.5.2
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/d9/5a/e7c31adbe875f2abbb91bd84cf2dc52d792b5a01506781dbcf25c91daf11/six-1.16.0-py2.py3-none-any.whl (11 kB)
Collecting markdown>=2.6.8
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/6e/33/1ae0f71395e618d6140fbbc9587cc3156591f748226075e0f7d6f9176522/Markdown-3.3.4-py3-none-any.whl (97 kB)
Collecting absl-py>=0.4
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/2c/03/e3e19d3faf430ede32e41221b294e37952e06acc96781c417ac25d4a0324/absl_py-1.0.0-py3-none-any.whl (126 kB)
Requirement already satisfied: setuptools>=41.0.0 in c:\users\ethan\.conda\envs\unity\lib\site-packages (from tensorboard>=1.15->mlagents) (58.0.4)
Collecting google-auth<3,>=1.6.3
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/6a/f7/06cbd5ebfba40a9d51df6217f9325317d824234400454aebcf014e2eee38/google_auth-2.3.3-py2.py3-none-any.whl (155 kB)
Collecting werkzeug>=0.11.15
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/1e/73/51137805d1b8d97367a8a77cae4a792af14bb7ce58fbd071af294c740cf0/Werkzeug-2.0.2-py3-none-any.whl (288 kB)
Collecting tensorboard-plugin-wit>=1.6.0
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/1a/c1/499e600ba0c618b451cd9c425ae1c177249940a2086316552fee7d86c954/tensorboard_plugin_wit-1.8.0-py3-none-any.whl (781 kB)
Requirement already satisfied: wheel>=0.26 in c:\users\ethan\.conda\envs\unity\lib\site-packages (from tensorboard>=1.15->mlagents) (0.37.0)
Collecting google-auth-oauthlib<0.5,>=0.4.1
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/b1/0e/0636cc1448a7abc444fb1b3a63655e294e0d2d49092dc3de05241be6d43c/google_auth_oauthlib-0.4.6-py2.py3-none-any.whl (18 kB)
Collecting tensorboard-data-server<0.7.0,>=0.6.0
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/74/69/5747a957f95e2e1d252ca41476ae40ce79d70d38151d2e494feb7722860c/tensorboard_data_server-0.6.1-py3-none-any.whl (2.4 kB)
Collecting requests<3,>=2.21.0
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/92/96/144f70b972a9c0eabbd4391ef93ccd49d0f2747f4f6a2a2738e99e5adc65/requests-2.26.0-py2.py3-none-any.whl (62 kB)
Collecting cachetools<5.0,>=2.0.0
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/ea/c1/4740af52db75e6dbdd57fc7e9478439815bbac549c1c05881be27d19a17d/cachetools-4.2.4-py3-none-any.whl (10 kB)
Collecting pyasn1-modules>=0.2.1
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/95/de/214830a981892a3e286c3794f41ae67a4495df1108c3da8a9f62159b9a9d/pyasn1_modules-0.2.8-py2.py3-none-any.whl (155 kB)
Collecting rsa<5,>=3.1.4
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/e9/93/0c0f002031f18b53af7a6166103c02b9c0667be528944137cc954ec921b3/rsa-4.7.2-py3-none-any.whl (34 kB)
Collecting requests-oauthlib>=0.7.0
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/a3/12/b92740d845ab62ea4edf04d2f4164d82532b5a0b03836d4d4e71c6f3d379/requests_oauthlib-1.3.0-py2.py3-none-any.whl (23 kB)
Collecting pyasn1<0.5.0,>=0.4.6
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/62/1e/a94a8d635fa3ce4cfc7f506003548d0a2447ae76fd5ca53932970fe3053f/pyasn1-0.4.8-py2.py3-none-any.whl (77 kB)
Requirement already satisfied: certifi>=2017.4.17 in c:\users\ethan\.conda\envs\unity\lib\site-packages (from requests<3,>=2.21.0->tensorboard>=1.15->mlagents) (2021.10.8)
Collecting idna<4,>=2.5
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/04/a2/d918dcd22354d8958fe113e1a3630137e0fc8b44859ade3063982eacd2a4/idna-3.3-py3-none-any.whl (61 kB)
Collecting urllib3<1.27,>=1.21.1
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/af/f4/524415c0744552cce7d8bf3669af78e8a069514405ea4fcbd0cc44733744/urllib3-1.26.7-py2.py3-none-any.whl (138 kB)
Collecting charset-normalizer~=2.0.0
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/de/c8/820b1546c68efcbbe3c1b10dd925fbd84a0dda7438bc18db0ef1fa567733/charset_normalizer-2.0.7-py3-none-any.whl (38 kB)
Collecting oauthlib>=3.0.0
Using cached https://pypi.tuna.tsinghua.edu.cn/packages/e8/5d/9dd1c29e5a786525f6342f6c1d812ed2e37edc653ad297048c1668988053/oauthlib-3.1.1-py2.py3-none-any.whl (146 kB)
Installing collected packages: urllib3, pyasn1, idna, charset-normalizer, six, rsa, requests, pyasn1-modules, oauthlib, cachetools, requests-oauthlib, google-auth, werkzeug, tensorboard-plugin-wit, tensorboard-data-server, pyyaml, pywin32, protobuf, Pillow, numpy, markdown, grpcio, google-auth-oauthlib, cloudpickle, attrs, absl-py, tensorboard, pypiwin32, mlagents-envs, h5py, cattrs, mlagents
Successfully installed Pillow-8.4.0 absl-py-1.0.0 attrs-21.2.0 cachetools-4.2.4 cattrs-1.6.0 charset-normalizer-2.0.7 cloudpickle-2.0.0 google-auth-2.3.3 google-auth-oauthlib-0.4.6 grpcio-1.41.1 h5py-3.5.0 idna-3.3 markdown-3.3.4 mlagents-0.27.0 mlagents-envs-0.27.0 numpy-1.21.4 oauthlib-3.1.1 protobuf-3.19.1 pyasn1-0.4.8 pyasn1-modules-0.2.8 pypiwin32-223 pywin32-302 pyyaml-6.0 requests-2.26.0 requests-oauthlib-1.3.0 rsa-4.7.2 six-1.16.0 tensorboard-2.7.0 tensorboard-data-server-0.6.1 tensorboard-plugin-wit-1.8.0 urllib3-1.26.7 werkzeug-2.0.2

(unity) C:\Users\Ethan>

之后我又使用命令 python -m pip --default-timeout=100 install tensorflow 并且连入移动4G网络提供的热点才下载完成。
最后的命令提示是这样的：
Successfully built termcolor
Installing collected packages: wrapt, typing-extensions, termcolor, tensorflow-io-gcs-filesystem, tensorflow-estimator, opt-einsum, libclang, keras-preprocessing, keras, google-pasta, gast, flatbuffers, astunparse, tensorflow
Successfully installed astunparse-1.6.3 flatbuffers-2.0 gast-0.4.0 google-pasta-0.2.0 keras-2.7.0 keras-preprocessing-1.1.2 libclang-12.0.0 opt-einsum-3.3.0 tensorflow-2.7.0 tensorflow-estimator-2.7.0 tensorflow-io-gcs-filesystem-0.22.0 termcolor-1.1.0 typing-extensions-3.10.0.2 wrapt-1.13.3

貌似安装好了，但是至于是否有版本匹配的问题，还不知道。

追评

谢谢老师，老师讲的非常简单易懂，算是入门了，希望老师能出更多这方面课程

老师讲得非常细致，希望老师以后出更多、更深入的Unity 人工智能教程。

我补充一下安装的注意事项吧，大部分都按照视频没问题，但是有些地方还是有报错，
如果torch报错的话，可以试试安装pip install torch==1.7.0+cpu torchvision==0.8.1+cpu torchaudio===0.7.0 -f https://download.pytorch.org/whl/torch_stable.html
如果mlagents-learn config.yaml时有报错说h5py报错，可能你的tensorflow版本是2.1，所以要换成和老师一样的2.2：pip install tensorflow-cpu==2.2.0 -i https://pypi.douban.com/simple/

好评好评！！最温柔的Lain老师讲的太棒了

Lain老师讲解清晰易懂，必须好评！

对unity又有了新的认识，unity引擎果然强大，跟着实操了一下，发现最大的问题居然是我的环境、包等等的安装，老师讲的很清楚，我跟着做了一遍，做出来了，好有成就感~，谢谢最温柔的Lain老师

一口气看完。感觉讲的非常好，但我只是看没实操，明天实操一下加深印象，考虑买之后的课程继续研究下，但可惜这属于python部分，想买unity A计划也想深入学习下python。哈哈 追评

很好

老师你好，我这边环境配置后终端输入mlagents-learn，之后在unity编辑器中点play场景还是原先的场景，并不会特别快速移动的去进行一遍又一遍的学习，这是什么原因 急谢谢

不错

可以，有意思

老师，安装mlagents期间原本正常，然后突然文字冒红是什么原因，无法安装成功，出现Error Exeption 追评

环境装不上，我们建议您使用--usefeature=2020 resolver在新解析器成为默认值之前测试包。

mlagents envs 0.18.1要求numpy<1.19.0，>=1.14.1，但是您将有numpy 1.19.1，这是不兼容的。

tensorflow 2.3.0要求numpy<1.19.0，>=1.16.0，但是您将有numpy 1.19.1，这是不兼容的。

模块安装不上

我用的你给的这个anaconda 版本不行， 我去网上有找了个2019.10的版本也不行

我用 --use-feature=2020-resolver 新的解释器安装上去 conda list 也可以显示出tensorflow这个包，但是 一训练就说找不到这个包

我前段时间在家里装的时候都没这些问题，好像pip要改什么东西吧

老师搞个GPU多人运动训练啊

不是没有激活，我感觉我得升级pip 但是升级报错
Installing collected packages: pip
Attempting uninstall: pip
Found existing installation: pip 20.2.1
Uninstalling pip-20.2.1:
ERROR: Could not install packages due to an EnvironmentError: [WinError 5] 拒绝访问。: 'e:\\anaconda\\envs\\ml-agents\\scripts\\pip.exe'
Consider using the `--user` option or check the permissions. 追评