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
 
 
 
 
 
GitHub c145e75b Split Policy and Optimizer, common Policy for PPO and SAC (#3345) 5 年前
..
doxygen Merge pull request #466 from Unity-Technologies/docs/doxygen 7 年前
images Merge commit 'f9c05a61d574305497789b5997f1ae3ea1b1ad3b' into develop-splitpolicyoptimizer 5 年前
localized Merge branch 'master' into develop-splitpolicyoptimizer 5 年前
API-Reference.md Fix Doxygen config (#3490) 5 年前
Background-Jupyter.md Release v0.5 (#1202) 6 年前
Background-Machine-Learning.md [docs] Fix typo. (#2260) 5 年前
Background-TensorFlow.md 1 to 1 Brain to Agent (#2729) 5 年前
Background-Unity.md Added background link to prefabs 6 年前
Basic-Guide.md Create ML-Agents Package (#3267) 5 年前
FAQ.md Convert Academy to a singleton (#3210) 5 年前
Feature-Memory.md 1 to 1 Brain to Agent (#2729) 5 年前
Feature-Monitor.md Don't inherit from Academy, remove virtual methods (#3184) 5 年前
Getting-Started-with-Balance-Ball.md Develop observation collector (#3352) 5 年前
Glossary.md Convert Academy to a singleton (#3210) 5 年前
Installation-Windows.md Create ML-Agents Package (#3267) 5 年前
Installation.md Update docs to reflect new package installation workflow. (#3362) 5 年前
Learning-Environment-Best-Practices.md Develop observation collector (#3352) 5 年前
Learning-Environment-Create-New.md Update Learning-Environment-Create-New.md (#3356) 5 年前
Learning-Environment-Design-Agents.md resolving merge conflicts 5 年前
Learning-Environment-Design.md Develop observation collector (#3352) 5 年前
Learning-Environment-Examples.md Update the curiosity mention in Hallway (#3386) 5 年前
Learning-Environment-Executable.md Create ML-Agents Package (#3267) 5 年前
Limitations.md [Documentation] Adding a few lines to mention that ML-Agents only works with NN generated with our trainers (#3426) 5 年前
ML-Agents-Overview.md Fixing the Docs on On Demand Decision (#3378) 5 年前
Migrating.md Split Policy and Optimizer, common Policy for PPO and SAC (#3345) 5 年前
Profiling-Python.md Make the timer output format consistent (#3472) 5 年前
Python-API.md Develop SideChannel new api (#3425) 5 年前
Readme.md landing page links to latest_release docs (#3415) 5 年前
Reward-Signals.md Fix typo in Reward Signals docs (#3420) 5 年前
Training-Curriculum-Learning.md Clarify curriculum and behavior name (#3380) 5 年前
Training-Generalized-Reinforcement-Learning-Agents.md Add missing backquote in generalized training docs (#3370) 5 年前
Training-Imitation-Learning.md Refactor DemonstrationStore/Recorder (#3354) 5 年前
Training-ML-Agents.md Temporarily remove multi-GPU 5 年前
Training-PPO.md Correct memory size docs 5 年前
Training-SAC.md Split Policy and Optimizer, common Policy for PPO and SAC (#3345) 5 年前
Training-Self-Play.md Fix typo in Self-Play docs (#3400) 5 年前
Training-Using-Concurrent-Unity-Instances.md fix trailing whitespace in markdown (#2786) 5 年前
Training-on-Amazon-Web-Service.md Rename mlagents.envs to mlagents_envs (#3083) 5 年前
Training-on-Microsoft-Azure-Custom-Instance.md fix trailing whitespace in markdown (#2786) 5 年前
Training-on-Microsoft-Azure.md move (first pass) 5 年前
Unity-Inference-Engine.md Support for ONNX export (#3101) 5 年前
Using-Docker.md Conda docker docs (#2982) 5 年前
Using-Tensorboard.md fix trailing whitespace in markdown (#2786) 5 年前
Using-Virtual-Environment.md docs updated (#2976) 5 年前
dox-ml-agents.conf Fix Doxygen config (#3490) 5 年前

Readme.md

Unity ML-Agents Toolkit Documentation

Installation & Set-up

Getting Started

Creating Learning Environments

Advanced Usage

Training

Advanced Training Methods

Inference

Help

API Docs

Translations

To make the Unity ML-Agents toolkit accessible to the global research and Unity developer communities, we're attempting to create and maintain translations of our documentation. We've started with translating a subset of the documentation to one language (Chinese), but we hope to continue translating more pages and to other languages. Consequently, we welcome any enhancements and improvements from the community.

Deprecated Docs

We no longer use them ourselves and so they may not be up-to-date. We've decided to keep them up just in case they are helpful to you.