Skip to content

MountainCar v0

Peter Mitrano edited this page Jan 1, 2017 · 13 revisions

Overview

Details

Name: MountainCar-v0
Category: Classic Control
Environment Page
Algorithms Page

Description

Get an under powered car to the top of a hill (top = 0.5 position)

Source

Andrew Moore in his PhD thesis [Moore90].

Environment

Observation

Type: Box(2)

Num Observation Min Max
0 position -1.2 0.6
1 velocity -0.07 0.07

Actions

Type: Discrete(3)

Num Observation Min Max
0 force on car -2.0 2.0
0 force on car -2.0 2.0

Reward

-1 for each time step, until the goal position of 0.5 is reached.

Starting State

Random angle from -pi to pi, and random velocity between -1 and 1

Episode Termination

There is no specified termination. Adding a maximum number of steps might be a good idea.

Solved Requirements

None yet specified