浏览代码

Update Agents-Editor-Interface.md

/develop-generalizationTraining-TrainerController
GitHub 7 年前
当前提交
c1abc3de
共有 1 个文件被更改,包括 8 次插入6 次删除
  1. 14
      docs/Agents-Editor-Interface.md

14
docs/Agents-Editor-Interface.md


# ML Agnets Editor Interface
# Academy
## Academy
![Academy Inspector](../raw/master/images/academy.png)

* `Target Frame Rate` - FPS engine attempts to maintain.
* `Default Reset Parameters` - List of custom parameters that can be changed in the environment on reset.
# Brain
## Brain
![Brain Inspector](../raw/master/images/brain.png)

* `Player` - Actions are decided using Player input mappings.
* `Heuristic` - Actions are decided using custom `Decision` script, which should be attached to the Brain game object.
## Internal Brain
### Internal Brain
![Internal Brain Inspector](../raw/master/images/internal_brain.png)

* `Min Value` and `Max Value` : Specify the range of the value here. The value will be sampled from the uniform distribution ranging from `Min Value` to `Max Value` inclusive.
## Player Brain
### Player Brain
# Agent
## Agent
* `Max Step` - The per-agent maximum number of steps. Once this number is reached, the agent will be reset if `Reset On Done` is checked.
* `Max Step` - The per-agent maximum number of steps. Once this number is reached, the agent will be reset if `Reset On Done` is checked.
正在加载...
取消
保存