Struct rsrl_domains::Acrobot

pub struct Acrobot(_);

Classic double pendulum control domain.

The acrobot is a 2-link pendulum environment in which only the second joint actuated. The goal is to swing the end-effector to a distance equal to the length of one link above the base.

See https://www.math24.net/double-pendulum/

Implementations

impl Acrobot

pub fn new(theta1: f64, theta2: f64, dtheta1: f64, dtheta2: f64) -> Acrobot

Trait Implementations

impl Default for Acrobot

fn default() -> Acrobot

Returns the "default value" for a type.

impl Domain for Acrobot

type StateSpace = ProductSpace<Interval>

State space representation type class.

type ActionSpace = Ordinal

Action space representation type class.

fn emit(&self) -> Observation<Vec<f64>>

Emit an observation of the current state of the environment.

fn step(&mut self, action: &usize) -> (Observation<Vec<f64>>, Reward)

Transition the environment forward a single step given an action, a.

fn state_space(&self) -> Self::StateSpace

Returns an instance of the state space type class.

fn action_space(&self) -> Ordinal

Returns an instance of the action space type class.

fn transition(
    &mut self,
    a: Action<Self>
) -> Transition<State<Self>, Action<Self>>

fn rollout<F>(
    self,
    pi: F,
    step_limit: Option<usize>
) -> Trajectory<State<Self>, Action<Self>> where
    F: FnMut(&State<Self>) -> Action<Self>,
    Self: Sized,