OpenAI Gym:理解`action_space` 符号(spaces.Box) [英] OpenAI Gym: Understanding `action_space` notation (spaces.Box)

查看:106
本文介绍了OpenAI Gym:理解`action_space` 符号(spaces.Box)的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!

问题描述

我想在 OpenAI CarRacing-v0 环境中设置一个 RL 代理,但在此之前我想了解动作空间.在 github 上的代码第 119 行中说:

I want to setup an RL agent on the OpenAI CarRacing-v0 environment, but before that I want to understand the action space. In the code on github line 119 says:

self.action_space = spaces.Box( np.array([-1,0,0]), np.array([+1,+1,+1]))  # steer, gas, brake

我如何阅读这一行?虽然我的问题是具体的 wrt CarRacing-v0 我想了解 spaces.Box() 一般的符号

How do I read this line? Although my problem is concrete wrt CarRacing-v0 I would like to understand the spaces.Box() notation in general

推荐答案

Box 意味着您正在处理实数值.

Box means that you are dealing with real valued quantities.

第一个数组 np.array([-1,0,0] 是可接受的最低值,第二个 np.array([+1,+1,+1]) 是可接受的最高值.在这种情况下(使用注释)我们看到我们有 3 个可用的操作:

The first array np.array([-1,0,0] are the lowest accepted values, and the second np.array([+1,+1,+1]) are the highest accepted values. In this case (using the comment) we see that we have 3 available actions:

  1. 转向:[-1, 1]
  2. Gas:[0, 1]
  3. 中的实际值
  4. Brake:[0, 1]
  5. 中的实值
  1. Steering: Real valued in [-1, 1]
  2. Gas: Real valued in [0, 1]
  3. Brake: Real valued in [0, 1]

这篇关于OpenAI Gym:理解`action_space` 符号(spaces.Box)的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!

查看全文
登录 关闭
扫码关注1秒登录
发送“验证码”获取 | 15天全站免登陆