Struct gym_rs::MountainCarEnv

pub struct MountainCarEnv { /* fields omitted */ }

Description: The agent (a car) is started at the bottom of a valley. For any given state, the agent may choose to accelerate to the left, right or cease any acceleration.

Source: The environment appeared first in Andrew Moore’s PhD Thesis (1990). the source code in python: https://www.github.com/openai/gym

Observation: Num Observation Min Max 0 Car Position -1.2 0.6 1 Car Velocity -0.07 0.07

Actions: In case of discrete action: Num Action 0 Accelerate to the left 1 Don’t accelerate 2 Accelerate to the right

In case of continuous action, apply a force in range [-1.0, 1.0],
1.0 being maximum acceleration to the right,
-1.0 being maximum acceleration to the left

Note: This does not affect the amount of velocity affected by the gravitational pull acting on the cart.

Reward: Reward of 0 is awarded if the agent reached the flag (position = 0.5) on top of the mountain. Reward of -1 is awarded if the position of the agent is less than 0.5.

Starting State: The position of the car is assigned a uniform random value in [-0.6, -0.4]. The starting velocity of the car is always assigned to 0.

Episode Termination: The car position is more than 0.5 Episode length is greater than 200

Implementations

impl MountainCarEnv

pub fn episode_length(&self) -> usize

Return the current length of the episode, which increases with each step

Trait Implementations

impl Debug for MountainCarEnv

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for MountainCarEnv

fn default() -> Self

Returns the “default value” for a type.

impl GymEnv for MountainCarEnv

fn step(&mut self, action: ActionType) -> (Vec<f64>, f64, bool, Option<String>)

Run one timestep of the environment’s dynamics. When end of episode is reached, you you are responsible for calling ‘reset()’ to reset this environment’s state

fn reset(&mut self) -> Vec<f64>

Reset the environment to an initial state This function should not reset reset the environment’s random number generator(s) Returns the environments initial state

fn render(&self, render: &mut GifRender<'_>)

render the environment using 30 frames per second

fn seed(&mut self, seed: u64)

Set the seed for this environments random number generator