Struct vrp_core::algorithms::mdp::Simulator[][src]

pub struct Simulator<S: State> { /* fields omitted */ }

A simulator to train agent with multiple episodes.

Implementations

impl<S: State> Simulator<S>[src]

pub fn new(
    learning_strategy: Box<dyn LearningStrategy<S> + Send + Sync>,
    policy_strategy: Box<dyn PolicyStrategy<S> + Send + Sync>
) -> Self
[src]

Creates a new instance of MDP simulator.

pub fn get_optimal_policy(
    &self,
    state: &S
) -> Option<(<S as State>::Action, f64)>
[src]

Return a learned optimal policy for given state.

pub fn get_state_estimates(&self) -> &StateEstimates<S>[src]

Gets state estimates.

pub fn set_action_estimates(&mut self, state: S, estimates: ActionEstimates<S>)[src]

Sets action estimates for given state.

pub fn run_episodes<A>(
    &mut self,
    agents: Vec<Box<A>>,
    parallelism: Parallelism,
    reducer: impl Fn(&S, &[f64]) -> f64
) -> Vec<Box<A>> where
    A: Agent<S> + Send + Sync
[src]

Runs single episode for each of the given agents in parallel.

Auto Trait Implementations

impl<S> !RefUnwindSafe for Simulator<S>

impl<S> Send for Simulator<S>

impl<S> Sync for Simulator<S>

impl<S> Unpin for Simulator<S> where
    S: Unpin,
    <S as State>::Action: Unpin

impl<S> !UnwindSafe for Simulator<S>

Blanket Implementations

impl<T> Any for T where
    T: 'static + ?Sized
[src]

impl<T> Borrow<T> for T where
    T: ?Sized
[src]

impl<T> BorrowMut<T> for T where
    T: ?Sized
[src]

impl<T> From<T> for T[src]

impl<T, U> Into<U> for T where
    U: From<T>, 
[src]

impl<T> Pointable for T

type Init = T

The type for initializers.

impl<T, U> TryFrom<U> for T where
    U: Into<T>, 
[src]

type Error = Infallible

The type returned in the event of a conversion error.

impl<T, U> TryInto<U> for T where
    U: TryFrom<T>, 
[src]

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.

impl<V, T> VZip<V> for T where
    V: MultiLane<T>,