Struct renforce::trainer::FittedQIteration

pub struct FittedQIteration<A: FiniteSpace> { /* fields omitted */ }

BatchTrainer for Q-functions Uses Fitted Q Iteration

Methods

impl<A: FiniteSpace> FittedQIteration<A>

fn new(action_space: A,
       gamma: f64,
       alpha: f64,
       iters: usize)
       -> FittedQIteration<A>

Creates a new FittedQIteration with the given parameters

fn default(action_space: A) -> FittedQIteration<A>

Creates a new FittedQIteration with default parameters

fn gamma(self, gamma: f64) -> FittedQIteration<A>

Sets gamma field of self

fn alpha(self, alpha: f64) -> FittedQIteration<A>

Sets alpha field of self

fn iters(self, iters: usize) -> FittedQIteration<A>

Sets iters field of self

Trait Implementations

impl<A: Debug + FiniteSpace> Debug for FittedQIteration<A> where A::Element: Debug

fn fmt(&self, __arg_0: &mut Formatter) -> Result

Formats the value using the given formatter.

impl<S: Space, A: FiniteSpace, T> BatchTrainer<S, A, T> for FittedQIteration<A> where T: QFunction<S, A> + Agent<S, A>

fn train(&mut self, agent: &mut T, transitions: Vec<Transition<S, A>>)

Trains agent based on the observed transitions