Andrew Cohen
4 年前
当前提交
ac261e36
共有 270 个文件被更改,包括 2751 次插入 和 2446 次删除
-
7.circleci/config.yml
-
6.pre-commit-config.yaml
-
6.yamato/com.unity.ml-agents-test.yml
-
8DevProject/Packages/manifest.json
-
4DevProject/ProjectSettings/ProjectVersion.txt
-
12Project/Assets/ML-Agents/Examples/3DBall/Scenes/3DBall.unity
-
12Project/Assets/ML-Agents/Examples/3DBall/Scenes/3DBallHard.unity
-
11Project/Assets/ML-Agents/Examples/3DBall/Scripts/Ball3DAgent.cs
-
11Project/Assets/ML-Agents/Examples/3DBall/Scripts/Ball3DHardAgent.cs
-
62Project/Assets/ML-Agents/Examples/Basic/Scenes/Basic.unity
-
15Project/Assets/ML-Agents/Examples/Bouncer/Scripts/BouncerAgent.cs
-
10Project/Assets/ML-Agents/Examples/Crawler/Scenes/CrawlerDynamicTarget.unity
-
6Project/Assets/ML-Agents/Examples/Crawler/Scripts/CrawlerAgent.cs
-
7Project/Assets/ML-Agents/Examples/FoodCollector/Scripts/FoodCollectorAgent.cs
-
1001Project/Assets/ML-Agents/Examples/GridWorld/Demos/ExpertGrid.demo
-
28Project/Assets/ML-Agents/Examples/GridWorld/Scenes/GridWorld.unity
-
12Project/Assets/ML-Agents/Examples/GridWorld/Scripts/GridAgent.cs
-
3Project/Assets/ML-Agents/Examples/GridWorld/Scripts/GridArea.cs
-
9Project/Assets/ML-Agents/Examples/Hallway/Scripts/HallwayAgent.cs
-
9Project/Assets/ML-Agents/Examples/PushBlock/Scripts/PushAgentBasic.cs
-
1001Project/Assets/ML-Agents/Examples/Pyramids/Demos/ExpertPyramid.demo
-
9Project/Assets/ML-Agents/Examples/Pyramids/Scripts/PyramidAgent.cs
-
6Project/Assets/ML-Agents/Examples/Reacher/Scripts/ReacherAgent.cs
-
2Project/Assets/ML-Agents/Examples/SharedAssets/Scripts/GroundContact.cs
-
8Project/Assets/ML-Agents/Examples/SharedAssets/Scripts/ModelOverrider.cs
-
10Project/Assets/ML-Agents/Examples/Soccer/Scripts/AgentSoccer.cs
-
2Project/Assets/ML-Agents/Examples/Soccer/Scripts/SoccerFieldArea.cs
-
34Project/Assets/ML-Agents/Examples/Startup/Scripts/Startup.cs
-
722Project/Assets/ML-Agents/Examples/Template/AgentPrefabsAndColors.unity
-
133Project/Assets/ML-Agents/Examples/Template/Scene.unity
-
4Project/Assets/ML-Agents/Examples/Template/Scripts/TemplateAgent.cs
-
4Project/Assets/ML-Agents/Examples/Tennis/Scripts/HitWall.cs
-
9Project/Assets/ML-Agents/Examples/Tennis/Scripts/TennisAgent.cs
-
9Project/Assets/ML-Agents/Examples/Walker/Scripts/WalkerAgent.cs
-
16Project/Assets/ML-Agents/Examples/WallJump/Scripts/WallJumpAgent.cs
-
4Project/Packages/manifest.json
-
5Project/ProjectSettings/ProjectSettings.asset
-
2Project/ProjectSettings/ProjectVersion.txt
-
110README.md
-
31com.unity.ml-agents/CHANGELOG.md
-
93com.unity.ml-agents/Documentation~/com.unity.ml-agents.md
-
69com.unity.ml-agents/Editor/BehaviorParametersEditor.cs
-
1com.unity.ml-agents/Editor/BrainParametersDrawer.cs
-
2com.unity.ml-agents/Editor/DemonstrationDrawer.cs
-
27com.unity.ml-agents/Editor/RayPerceptionSensorComponentBaseEditor.cs
-
36com.unity.ml-agents/Runtime/Academy.cs
-
149com.unity.ml-agents/Runtime/Agent.cs
-
22com.unity.ml-agents/Runtime/Communicator/GrpcExtensions.cs
-
22com.unity.ml-agents/Runtime/Communicator/ICommunicator.cs
-
92com.unity.ml-agents/Runtime/Communicator/RpcCommunicator.cs
-
9com.unity.ml-agents/Runtime/DecisionRequester.cs
-
1com.unity.ml-agents/Runtime/Demonstrations/Demonstration.cs
-
13com.unity.ml-agents/Runtime/Demonstrations/DemonstrationRecorder.cs
-
3com.unity.ml-agents/Runtime/Demonstrations/DemonstrationWriter.cs
-
1com.unity.ml-agents/Runtime/DiscreteActionMasker.cs
-
74com.unity.ml-agents/Runtime/Grpc/CommunicatorObjects/UnityRlInitializationInput.cs
-
79com.unity.ml-agents/Runtime/Grpc/CommunicatorObjects/UnityRlInitializationOutput.cs
-
15com.unity.ml-agents/Runtime/SideChannels/SideChannel.cs
-
12com.unity.ml-agents/Runtime/SideChannels/RawBytesChannel.cs
-
111com.unity.ml-agents/Runtime/SideChannels/FloatPropertiesChannel.cs
-
33com.unity.ml-agents/Runtime/SideChannels/EngineConfigurationChannel.cs
-
2com.unity.ml-agents/Runtime/Sensors/WriteAdapter.cs
-
57com.unity.ml-agents/Runtime/Sensors/RenderTextureSensorComponent.cs
-
28com.unity.ml-agents/Runtime/Sensors/RenderTextureSensor.cs
-
75com.unity.ml-agents/Runtime/Sensors/RayPerceptionSensorComponentBase.cs
-
8com.unity.ml-agents/Runtime/Sensors/RayPerceptionSensorComponent3D.cs
-
29com.unity.ml-agents/Runtime/Sensors/RayPerceptionSensor.cs
-
82com.unity.ml-agents/Runtime/Sensors/CameraSensorComponent.cs
-
19com.unity.ml-agents/Runtime/Sensors/CameraSensor.cs
-
2com.unity.ml-agents/Runtime/Policies/RemotePolicy.cs
-
2com.unity.ml-agents/Runtime/Policies/IPolicy.cs
-
91com.unity.ml-agents/Runtime/Policies/HeuristicPolicy.cs
-
18com.unity.ml-agents/Runtime/Policies/BrainParameters.cs
-
164com.unity.ml-agents/Runtime/Policies/BehaviorParameters.cs
-
6com.unity.ml-agents/Runtime/Policies/BarracudaPolicy.cs
-
2com.unity.ml-agents/Runtime/Inference/Utils/RandomNormal.cs
-
2com.unity.ml-agents/Runtime/Inference/Utils/Multinomial.cs
-
4com.unity.ml-agents/Runtime/Inference/TensorProxy.cs
-
2com.unity.ml-agents/Runtime/Inference/TensorNames.cs
-
2com.unity.ml-agents/Runtime/Inference/TensorGenerator.cs
-
4com.unity.ml-agents/Runtime/Inference/TensorApplier.cs
-
5com.unity.ml-agents/Runtime/Inference/ModelRunner.cs
-
6com.unity.ml-agents/Runtime/Inference/GeneratorImpl.cs
-
19com.unity.ml-agents/Runtime/Inference/BarracudaModelParamLoader.cs
-
4com.unity.ml-agents/Runtime/Inference/ApplierImpl.cs
-
3com.unity.ml-agents/Tests/Editor/DemonstrationTests.cs
-
4com.unity.ml-agents/Tests/Editor/DiscreteActionOutputApplierTest.cs
-
1com.unity.ml-agents/Tests/Editor/EditModeTestActionMasker.cs
-
5com.unity.ml-agents/Tests/Editor/EditModeTestInternalBrainTensorApplier.cs
-
8com.unity.ml-agents/Tests/Editor/EditModeTestInternalBrainTensorGenerator.cs
-
225com.unity.ml-agents/Tests/Editor/MLAgentsEditModeTest.cs
-
3com.unity.ml-agents/Tests/Editor/ModelRunnerTest.cs
-
2com.unity.ml-agents/Tests/Editor/MultinomialTest.cs
-
3com.unity.ml-agents/Tests/Editor/ParameterLoaderTest.cs
-
2com.unity.ml-agents/Tests/Editor/RandomNormalTest.cs
-
2com.unity.ml-agents/Tests/Editor/Sensor/WriterAdapterTests.cs
-
72com.unity.ml-agents/Tests/Editor/SideChannelTests.cs
-
4com.unity.ml-agents/Tests/Editor/TensorUtilsTest.cs
-
4com.unity.ml-agents/package.json
-
2config/sac_trainer_config.yaml
|
|||
m_EditorVersion: 2019.3.0f6 |
|||
m_EditorVersionWithRevision: 2019.3.0f6 (27ab2135bccf) |
|||
m_EditorVersion: 2019.3.3f1 |
|||
m_EditorVersionWithRevision: 2019.3.3f1 (7ceaae5f7503) |
1001
Project/Assets/ML-Agents/Examples/GridWorld/Demos/ExpertGrid.demo
文件差异内容过多而无法显示
查看文件
文件差异内容过多而无法显示
查看文件
1001
Project/Assets/ML-Agents/Examples/Pyramids/Demos/ExpertPyramid.demo
文件差异内容过多而无法显示
查看文件
文件差异内容过多而无法显示
查看文件
722
Project/Assets/ML-Agents/Examples/Template/AgentPrefabsAndColors.unity
文件差异内容过多而无法显示
查看文件
文件差异内容过多而无法显示
查看文件
|
|||
m_EditorVersion: 2018.4.14f1 |
|||
m_EditorVersion: 2018.4.18f1 |
|
|||
Please see the [ML-Agents README)(https://github.com/Unity-Technologies/ml-agents/blob/master/README.md) |
|||
# About ML-Agents package (`com.unity.ml-agents`) |
|||
|
|||
The Unity ML-Agents package contains the C# SDK for the |
|||
[Unity ML-Agents Toolkit](https://github.com/Unity-Technologies/ml-agents). |
|||
|
|||
The package provides the ability for any Unity scene to be converted into a learning |
|||
environment where character behaviors can be trained using a variety of machine learning |
|||
algorithms. Additionally, it enables any trained behavior to be embedded back into the Unity |
|||
scene. More specifically, the package provides the following core functionalities: |
|||
* Define Agents: entities whose behavior will be learned. Agents are entities |
|||
that generate observations (through sensors), take actions and receive rewards from |
|||
the environment. |
|||
* Define Behaviors: entities that specifiy how an agent should act. Multiple agents can |
|||
share the same Behavior and a scene may have multiple Behaviors. |
|||
* Record demonstrations of an agent within the Editor. These demonstrations can be |
|||
valuable to train a behavior for that agent. |
|||
* Embedding a trained behavior into the scene via the |
|||
[Unity Inference Engine](https://docs.unity3d.com/Packages/com.unity.barracuda@latest/index.html). |
|||
Thus an Agent can switch from a learning behavior to an inference behavior. |
|||
|
|||
Note that this package does not contain the machine learning algorithms for training |
|||
behaviors. It relies on a Python package to orchestrate the training. This package |
|||
only enables instrumenting a Unity scene and setting it up for training, and then |
|||
embedding the trained model back into your Unity scene. |
|||
|
|||
## Preview package |
|||
This package is available as a preview, so it is not ready for production use. |
|||
The features and documentation in this package might change before it is verified for release. |
|||
|
|||
|
|||
## Package contents |
|||
|
|||
The following table describes the package folder structure: |
|||
|
|||
|**Location**|**Description**| |
|||
|---|---| |
|||
|*Documentation~*|Contains the documentation for the Unity package.| |
|||
|*Editor*|Contains utilities for Editor windows and drawers.| |
|||
|*Plugins*|Contains third-party DLLs.| |
|||
|*Runtime*|Contains core C# APIs for integrating ML-Agents into your Unity scene. | |
|||
|*Tests*|Contains the unit tests for the package.| |
|||
|
|||
<a name="Installation"></a> |
|||
|
|||
## Installation |
|||
|
|||
To install this package, follow the instructions in the |
|||
[Package Manager documentation](https://docs.unity3d.com/Manual/upm-ui-install.html). |
|||
|
|||
To install the Python package to enable training behaviors, follow the instructions on our |
|||
[GitHub repository](https://github.com/Unity-Technologies/ml-agents/blob/latest_release/docs/Installation.md). |
|||
|
|||
## Requirements |
|||
|
|||
This version of the Unity ML-Agents package is compatible with the following versions of the Unity Editor: |
|||
|
|||
* 2018.4 and later (recommended) |
|||
|
|||
## Known limitations |
|||
|
|||
### Headless Mode |
|||
|
|||
If you enable Headless mode, you will not be able to collect visual observations |
|||
from your agents. |
|||
|
|||
### Rendering Speed and Synchronization |
|||
|
|||
Currently the speed of the game physics can only be increased to 100x real-time. |
|||
The Academy also moves in time with FixedUpdate() rather than Update(), so game |
|||
behavior implemented in Update() may be out of sync with the agent decision |
|||
making. See |
|||
[Execution Order of Event Functions](https://docs.unity3d.com/Manual/ExecutionOrder.html) |
|||
for more information. |
|||
|
|||
You can control the frequency of Academy stepping by calling |
|||
`Academy.Instance.DisableAutomaticStepping()`, and then calling |
|||
`Academy.Instance.EnvironmentStep()` |
|||
|
|||
### Unity Inference Engine Models |
|||
Currently, only models created with our trainers are supported for running |
|||
ML-Agents with a neural network behavior. |
|||
|
|||
|
|||
## Helpful links |
|||
|
|||
If you are new to the Unity ML-Agents package, or have a question after reading |
|||
the documentation, you can checkout our |
|||
[GitHUb Repository](https://github.com/Unity-Technologies/ml-agents), which |
|||
also includes a number of ways to |
|||
[connect with us](https://github.com/Unity-Technologies/ml-agents#community-and-feedback) |
|||
including our [ML-Agents Forum](https://forum.unity.com/forums/ml-agents.453/). |
|||
|
|
|||
{ |
|||
"name": "com.unity.ml-agents", |
|||
"displayName":"ML Agents", |
|||
"version": "0.14.1-preview", |
|||
"version": "0.15.0-preview", |
|||
"com.unity.barracuda": "0.6.0-preview" |
|||
"com.unity.barracuda": "0.6.1-preview" |
|||
} |
|||
} |
部分文件因为文件数量过多而无法显示
撰写
预览
正在加载...
取消
保存
Reference in new issue