【gym】【离散动作空间】【Mountain Car 山地车】

目录

Mountain Car 山地车

Description 描述

Observation Space观测空间

Action Space 动作空间

Transition Dynamics:过渡动态：

Reward: 奖励：

Starting State起始状态

Episode End 回合结束

Arguments 参数

Version History版本历史记录

---

Mountain Car 山地车

        This environment is part of the Classic Control environments. Please read that page first for general information.
        此环境是经典控制环境的一部分。请先阅读该页面以获取一般信息。

Action Space  动作空间	Discrete(3)
Observation Shape 状态形状	(2,)
Observation High  状态上限	[0.6 0.07]
Observation Low  状态下限	[-1.2 -0.07]
Import	gym.make("MountainCar-v0")

Description 描述

        The Mountain Car MDP is a deterministic MDP that consists of a car placed stochastically at the bottom of a sinusoidal valley, with the only possible actions being the accelerations that can be applied to the car in either direction. The goal of the MDP is to strategically accelerate the car to reach the goal state on top of the right hill. There are two versions of th