Enum RlAlgorithm 

pub enum RlAlgorithm {
    QLearning {
        alpha: f64,
        gamma: f64,
        epsilon: f64,
    },
    Sarsa {
        alpha: f64,
        gamma: f64,
        epsilon: f64,
    },
    DoubleQLearning {
        alpha: f64,
        gamma: f64,
        epsilon: f64,
    },
}

Reinforcement learning algorithm variant.

Variants

QLearning

Off-policy TD(0) with greedy target policy.

Fields

alpha: f64

Learning rate α ∈ (0, 1].

gamma: f64

Discount factor γ ∈ [0, 1].

epsilon: f64

Exploration rate ε ∈ [0, 1] for on-policy action selection.

Sarsa

On-policy TD(0) — the target action is chosen by the current ε-greedy policy.

Fields

alpha: f64

Learning rate α ∈ (0, 1].

gamma: f64

Discount factor γ ∈ [0, 1].

epsilon: f64

Exploration rate ε ∈ [0, 1].

DoubleQLearning

Double Q-learning — maintains two independent Q-tables and randomly selects which to update at each step, reducing the maximisation bias present in standard Q-learning.

Fields

alpha: f64

Learning rate α ∈ (0, 1].

gamma: f64

Discount factor γ ∈ [0, 1].

epsilon: f64

Exploration rate ε ∈ [0, 1].

Implementations

impl RlAlgorithm

pub fn hyperparams(&self) -> (f64, f64, f64)

Return the (alpha, gamma, epsilon) triple regardless of variant.

Trait Implementations

impl Clone for RlAlgorithm

fn clone(&self) -> RlAlgorithm

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RlAlgorithm

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

Formats the value using the given formatter.

impl PartialEq for RlAlgorithm

fn eq(&self, other: &RlAlgorithm) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for RlAlgorithm