浏览代码

Minor tweak to Feature-ODD to address PR comments.

/develop-generalizationTraining-TrainerController
Marwan Mattar 7 年前
当前提交
f9cfc41c
共有 1 个文件被更改,包括 1 次插入1 次删除
  1. 2
      docs/Feature-On-Demand-Decisions.md

2
docs/Feature-On-Demand-Decisions.md


Agent will reuse the decision the Brain has given it.
* If `On Demand Decisions` is checked, the Agent controls when to receive
decisions and actions. To do so, the Agent may leverage one or two methods:
decisions, and take actions. To do so, the Agent may leverage one or two methods:
* `RequestDecision()` Signals that the Agent is requesting a decision.
This causes the Agent to collect its observations and ask the Brain for a
decision at the next step of the simulation. Note that when an Agent

正在加载...
取消
保存