Struct renforce::trainer::CrossEntropy

pub struct CrossEntropy<F: Float> { /* fields omitted */ }

Cross Entropy method for parameter selection

Methods

impl<F: Float> CrossEntropy<F>

fn new(elite: f64,
       num_samples: usize,
       eval_period: TimePeriod,
       iters: usize)
       -> CrossEntropy<F>

Constructs a new CrossEntropy

fn elite(self, elite: f64) -> CrossEntropy<F>

Updates elite field of self

fn num_samples(self, num_samples: usize) -> CrossEntropy<F>

Updates num_samples field of self

fn eval_period(self, eval_period: TimePeriod) -> CrossEntropy<F>

Updates eval_period field of self

fn iters(self, iters: usize) -> CrossEntropy<F>

Updates iters field of self

Trait Implementations

impl<F: Debug + Float> Debug for CrossEntropy<F>

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

Formats the value using the given formatter.

impl<F: Float, S: Space, A: Space, T> EpisodicTrainer<S, A, T> for CrossEntropy<F> where T: Agent<S, A> + ParameterizedFunc<F>

fn train_step(&mut self,
              agent: &mut T,
              env: &mut Environment<State=S, Action=A>)

Trains agent using 1 "episodes" worth of exploration

fn train(&mut self, agent: &mut T, env: &mut Environment<State=S, Action=A>)

Trains agent to perform well in the environment, potentially acting out multiple episodes

impl<F: Float> Default for CrossEntropy<F>

fn default() -> CrossEntropy<F>

Creates a new CrossEntropy with some default values