Mountain Car

lerax.env.MountainCar

Bases: AbstractClassicControlEnv[MountainCarState, Int[Array, ''], Float[Array, '2']]

Mountain Car environment matching the Gymnasium MountainCar environment.

Note

To achieve identical dynamics to Gymnasium set solver=diffrax.Euler().

Action Space

The action space is discrete with 3 actions:

0: Push left
1: No push
2: Push right

The action applies a fixed magnitude force to the car in the specified direction for the duration of the time step.

Observation Space

The observation space is a 2-dimensional continuous space representing the position and velocity of the car:

Index	Observation	Min Value	Max Value
0	Car Position	-1.2	0.6
1	Car Velocity	-0.07	0.07

These values reflect the physical limits of the environment. These limits can be modified via the min_position, max_position, and max_speed parameters.

Reward

The reward is -1 for every step taken until the goal position is reached.

Termination

The episode terminates when the car reaches the goal position of 0.5 with a velocity of at least 0.0.

Parameters:

Name	Type	Description	Default
`min_position`	`Float[ArrayLike, '']`	Minimum position of the car.	`-1.2`
`max_position`	`Float[ArrayLike, '']`	Maximum position of the car.	`0.6`
`max_speed`	`Float[ArrayLike, '']`	Maximum speed of the car.	`0.07`
`goal_position`	`Float[ArrayLike, '']`	Position at which the episode terminates.	`0.5`
`goal_velocity`	`Float[ArrayLike, '']`	Minimum velocity at the goal position to terminate the episode.	`0.0`
`force`	`Float[ArrayLike, '']`	Magnitude of the force applied when pushing the car.	`0.001`
`gravity`	`Float[ArrayLike, '']`	Gravity constant affecting the car's movement.	`0.0025`
`dt`	`Float[ArrayLike, '']`	Time step for the environment dynamics.	`1.0`
`solver`	`diffrax.AbstractSolver \| None`	Diffrax solver to use for integrating the dynamics.	`None`
`stepsize_controller`	`diffrax.AbstractStepSizeController \| None`	Step size controller for adaptive solvers.	`None`