# Unity ML - Agents (Editor SDK)
![diagram](../images/agents_diagram.png)
## Unity Setup
Make sure you have Unity 2017.1 or later installed. Download link available [here](https://store.unity.com/download?ref=update).
### Building a Unity Environment
- (1) Open the project in the Unity editor *(If this is not first time running Unity, you'll be able to skip most of these immediate steps, choose directly from the list of recently opened projects and jump directly to )*
- On the initial dialog, choose `Open` on the top options
- On the file dialog, choose `ProjectName` and click `Open` *(It is safe to ignore any warning message about non-matching editor installation")*
- Once the project is open, on the `Project` panel (bottom of the tool), click the top folder for `Assets`
- Double-click the scene icon (Unity logo) to load all game assets
- (2) *File -> Build Settings*
- (3) Choose your target platform:
- (opt) Select “Developer Build” to log debug messages.
- (4) Set architecture: `X86_64`
- (5) Click *Build*:
- Save environment binary to a sub-directory containing the model to use for training *(you may need to click on the down arrow on the file chooser to be able to select that folder)*
## Example Projects
The `Examples` subfolder contains a set of example environments to use either as starting points or templates for designing your own environments.
* **3DBalanceBall** - Physics-based game where the agent must rotate a 3D-platform to keep a ball in the air. Supports both discrete and continuous control.
* **GridWorld** - A simple gridworld containing regions which provide positive and negative reward. The agent must learn to move to the rewarding regions (green) and avoid the negatively rewarding ones (red). Supports discrete control.
* **Tennis** - An adversarial game where two agents control rackets, which must be used to bounce a ball back and forth between them. Supports continuous control.
For more informoation on each of these environments, see this [documentation page](../docs/Example-Environments.md).
Within `ML-Agents/Template` there also exists:
* **Template** - An empty Unity scene with a single _Academy_, _Brain_, and _Agent_. Designed to be used as a template for new environments.
## Agents SDK Package
A link to Unity package containing the Agents SDK for Unity 2017.1 can be downloaded here :
* [ML-Agents package without TensorflowSharp](https://s3.amazonaws.com/unity-agents/ML-AgentsNoPlugin.unitypackage)
* [ML-Agents package with TensorflowSharp](https://s3.amazonaws.com/unity-agents/ML-AgentsWithPlugin.unitypackage)
For information on the use of each script, see the comments and documentation within the files themselves, or read the [documentation](../../../wiki).
## Creating your own Unity Environment
For information on how to create a new Unity Environment, see the walkthrough [here](../docs/Making-a-new-Unity-Environment.md). If you have questions or run into issues, please feel free to create issues through the repo, and we will do our best to address them.
## Embedding Models with TensorflowSharp _[Experimental]_
If you will be using Tensorflow Sharp in Unity, you must:
1. Make sure you are using Unity 2017.1 or newer.
2. Make sure the TensorflowSharp plugin is in your Asset folder. A Plugins folder which includes TF# can be downloaded [here](https://s3.amazonaws.com/unity-agents/TFSharpPlugin.unitypackage).
3. Go to `Edit` -> `Project Settings` -> `Player`
4. For each of the platforms you target (**`PC, Mac and Linux Standalone`**, **`iOS`** or **`Android`**):
1. Go into `Other Settings`.
2. Select `Scripting Runtime Version` to `Experimental (.NET 4.6 Equivalent)`
3. In `Scripting Defined Symbols`, add the flag `ENABLE_TENSORFLOW`
5. Restart the Unity Editor.
没有合适的资源?快使用搜索试试~ 我知道了~
ml-agents-master
共229个文件
meta:99个
cs:28个
mat:18个
5星 · 超过95%的资源 需积分: 10 38 下载量 54 浏览量
2017-10-19
17:38:16
上传
评论 1
收藏 4.23MB ZIP 举报
温馨提示
unity和python对接的unity包,里面包括完整的文档和环境,当然在github上也可以下载
资源推荐
资源详情
资源评论
收起资源包目录
ml-agents-master (229个子文件)
ProjectSettings.asset 16KB
InputManager.asset 6KB
QualitySettings.asset 5KB
GraphicsSettings.asset 2KB
Physics2DSettings.asset 1KB
NavMeshAreas.asset 1KB
UnityConnectSettings.asset 775B
DynamicsManager.asset 737B
EditorBuildSettings.asset 482B
EditorSettings.asset 455B
TagManager.asset 378B
AudioManager.asset 357B
TimeManager.asset 202B
NetworkManager.asset 151B
ClusterInputManager.asset 114B
GridWorld.bytes 860KB
Tennis.bytes 20KB
3DBall.bytes 20KB
Brain.cs 16KB
CoreBrainInternal.cs 13KB
ExternalCommunicator.cs 11KB
Academy.cs 9KB
Agent.cs 7KB
AgentMonitor.cs 6KB
GridAgent.cs 5KB
CoreBrainPlayer.cs 4KB
GridAcademy.cs 4KB
Ball3DAgent.cs 4KB
hitWall.cs 4KB
TennisAgent.cs 3KB
CoreBrainHeuristic.cs 3KB
CoreBrainExternal.cs 2KB
Communicator.cs 2KB
BrainEditor.cs 2KB
BasicAgent.cs 2KB
Decision.cs 1KB
TennisAcademy.cs 779B
CoreBrain.cs 778B
UnityAgentsException.cs 751B
Ball3DDecision.cs 671B
TemplateDecision.cs 439B
BasicDecision.cs 436B
TemplateAgent.cs 373B
Ball3DAcademy.cs 230B
TemplateAcademy.cs 218B
BasicAcademy.cs 213B
Newtonsoft.Json.dll 473KB
.gitignore 1KB
PPO.ipynb 6KB
Basics.ipynb 5KB
floor.jpg 885KB
LICENSE 11KB
UIDefault.mat 2KB
Text.mat 2KB
logo 1.mat 2KB
Floor.mat 2KB
None.mat 2KB
sand.mat 2KB
logo 2.mat 2KB
floor.mat 2KB
invisible.mat 2KB
logo.mat 2KB
ball.mat 2KB
goal_mat.mat 2KB
agent_mat.mat 2KB
pit_mat.mat 2KB
Wall.mat 2KB
goal.mat 2KB
agent.mat 2KB
NetMat.mat 2KB
Making-a-new-Unity-Environment.md 15KB
Getting-Started-with-Balance-Ball.md 8KB
Unity-Agents-Overview.md 7KB
Using-TensorFlow-Sharp-in-Unity-(Experimental).md 6KB
Agents-Editor-Interface.md 5KB
README.md 4KB
Unity-Agents---Python-API.md 4KB
Example-Environments.md 3KB
CODE_OF_CONDUCT.md 3KB
Limitations-&-Common-Issues.md 3KB
Training-on-Amazon-Web-Service.md 3KB
installation.md 2KB
README.md 2KB
Organizing-the-Scene.md 2KB
README.md 1KB
best-practices.md 1KB
Readme.md 901B
Racket.obj.meta 2KB
logo.png.meta 2KB
RacketTex.png.meta 2KB
floor.jpg.meta 2KB
Newtonsoft.Json.dll.meta 486B
BrainEditor.cs.meta 263B
Brain.cs.meta 263B
Communicator.cs.meta 263B
CoreBrainPlayer.cs.meta 263B
CoreBrainHeuristic.cs.meta 263B
CoreBrain.cs.meta 263B
Decision.cs.meta 263B
TemplateDecision.cs.meta 263B
共 229 条
- 1
- 2
- 3
资源评论
- KAila_Lucky2019-03-27蛮好的,挺好的
- andrewfungxx2018-09-15可以用,不过是从github下了
软硬兼吃曹达华
- 粉丝: 148
- 资源: 11
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- Screenshot_20240427_031602.jpg
- 网页PDF_2024年04月26日 23-46-14_QQ浏览器网页保存_QQ浏览器转格式(6).docx
- 直接插入排序,冒泡排序,直接选择排序.zip
- 在排序2的基础上,再次对快排进行优化,其次增加快排非递归,归并排序,归并排序非递归版.zip
- 实现了7种排序算法.三种复杂度排序.三种nlogn复杂度排序(堆排序,归并排序,快速排序)一种线性复杂度的排序.zip
- 冒泡排序 直接选择排序 直接插入排序 随机快速排序 归并排序 堆排序.zip
- 课设-内部排序算法比较 包括冒泡排序、直接插入排序、简单选择排序、快速排序、希尔排序、归并排序和堆排序.zip
- Python排序算法.zip
- C语言实现直接插入排序、希尔排序、选择排序、冒泡排序、堆排序、快速排序、归并排序、计数排序,并带图详解.zip
- 常用工具集参考用于图像等数据处理
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功