unity-tech-cn
/
ml-agents
46
14
派生 39
代码 合并请求 版本发布
Unity 机器学习代理工具包 (ML-Agents) 是一个开源项目，它使游戏和模拟能够作为训练智能代理的环境。
您最多选择25个主题 主题必须以中文或者字母或数字开头，可以包含连字符 (-)，并且长度不得超过35个字符
15 提交
337 分支
128 Plastic标签
 
 
 
 
 
目录树: 5108ec97
分支列表 标签列表
${ item.name }
创建分支 ${ searchTerm }
从 '5108ec97'
${ noResults }
ml-agents/ml-agents
GitHub 5108ec97 Update ml-agents/mlagents/trainers/model_saver/torch_model_saver.py 4 年前
..
mlagents Update ml-agents/mlagents/trainers/model_saver/torch_model_saver.py 4 年前
tests Automatically generate samples based on placement of mlagents-sample.json files in our examples. (#5077) 4 年前
README.md [release_15] Release 15 update versions (#5101) 4 年前
setup.py Update v2-staging from main (March 15) (#5123) 4 年前

README.md

Unity ML-Agents Trainers

The mlagents Python package is part of the ML-Agents Toolkit. mlagents provides a set of reinforcement and imitation learning algorithms designed to be used with Unity environments. The algorithms interface with the Python API provided by the mlagents_envs package. See here for more information on mlagents_envs.

The algorithms can be accessed using the: mlagents-learn access point. See here for more information on using this package.

Installation

Install the mlagents package with:

python -m pip install mlagents==0.25.0

Usage & More Information

For more information on the ML-Agents Toolkit and how to instrument a Unity scene with the ML-Agents SDK, check out the main ML-Agents Toolkit documentation.

Limitations

  • mlagents does not yet explicitly support multi-agent scenarios so training cooperative behavior among different agents is not stable.
  • Resuming self-play from a checkpoint resets the reported ELO to the default value.