Struct renforce::trainer::SARSALearner

pub struct SARSALearner { /* fields omitted */ }

Represents an OnlineTrainer for Q-functions Uses the SARSA algorithm

Methods

impl SARSALearner

fn new(gamma: f64, alpha: f64, train_period: TimePeriod) -> SARSALearner

Returns a new SARSALearner with the given info

fn gamma(self, gamma: f64) -> SARSALearner

Sets gamma field of self

fn alpha(self, alpha: f64) -> SARSALearner

Sets alpha field of self

fn train_period(self, train_period: TimePeriod) -> SARSALearner

Sets train_period field of self

Trait Implementations

impl Debug for SARSALearner

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

Formats the value using the given formatter.

impl<T, S: Space, A: Space> OnlineTrainer<S, A, T> for SARSALearner where T: QFunction<S, A> + Agent<S, A>

fn train_step(&mut self, agent: &mut T, transition: Transition<S, A>)

Performs one training iteration using the given transition

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

Automatically trains the agent to perform well in the environment

impl Default for SARSALearner

fn default() -> SARSALearner

Creates a new SARSALearner with default values for gamma, alpha, and train_period