Struct ThompsonSampling 

pub struct ThompsonSampling {
    pub random_state: Option<u64>,
    /* private fields */
}

Thompson Sampling strategy for multi-armed bandit active learning

This strategy uses Bayesian inference to maintain probability distributions over the reward rates of each arm and samples from these distributions.

Fields

random_state: Option<u64>

random_state

Implementations

impl ThompsonSampling

pub fn new() -> Self

pub fn random_state(self, random_state: u64) -> Self

pub fn initialize(&mut self, n_arms: usize)

pub fn select_arm(&mut self) -> Result<usize>

pub fn update(&mut self, arm_idx: usize, reward: f64) -> Result<()>

pub fn get_arm_statistics(&self) -> Vec<(f64, f64, f64, f64)>

Trait Implementations

impl Clone for ThompsonSampling

fn clone(&self) -> ThompsonSampling

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ThompsonSampling

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for ThompsonSampling

fn default() -> Self

Returns the “default value” for a type.